作者Jared Moore, Andrea Mock, Yifan Mai, Jacy Reese Anthis, Ryan Louie, William Agnew, Ashish Mehta, Kevin Klyman, Percy Liang, Nick Haber, Eric Lin, Desmond C. Ong
Mental health professionals have raised concerns about risks of psychological harm from interaction with large language models (LLMs), including "delusional spirals" in which concerning human and LLM behaviors reinforce each other over time. With growing public use of LLM-powered chatbots, there is an urgent need to build evaluations grounded in real-world episodes of psychological harm experienced by users. We developed DelusionEval, an evaluation protocol that tests a model's tendencies to exhibit behaviors linked to promoting user delusions. We prompt each model with 589 unique conversation histories from 18 participants, comprising 12,591 messages from users who experienced delusions and psychological harm. We find that the tendency of an evaluated LLM to exhibit delusion-linked behavior does not reliably correlate with model size, release date, or the presence of test-time reasoning. However, extending the context of prior messages substantially increases rates of delusion-linked behaviors, providing evidence for the importance of context in LLM safety evaluation. For example, the rate of failing to discourage self-harm when the user expresses suicidal ideation increases from 30.0% to 41.1% when an additional 350 messages are prepended to the conversation history. All model families (e.g., GPT, Claude) exhibit substantial rates of delusion-linked behaviors. Within families, later, larger, or higher-reasoning models are not uniformly better across all behavior categories. Our results raise concerns regarding the potential psychological impact of LLMs and the need for more rigorous studies of real-world human-AI interaction.
展开完整摘要收起摘要↓
Mental health professionals have raised concerns about risks of psychological harm from interaction with large language models (LLMs), including "delusional spirals" in which concerning human and LLM behaviors reinforce each other over time. With growing public use of LLM-powered chatbots, there is an urgent need to build evaluations grounded in real-world episodes of psychological harm experienced by users. We developed DelusionEval, an evaluation protocol that tests a model's tendencies to exhibit behaviors linked to promoting user delusions. We prompt each model with 589 unique conversation histories from 18 participants, comprising 12,591 messages from users who experienced delusions and psychological harm. We find that the tendency of an evaluated LLM to exhibit delusion-linked behavior does not reliably correlate with model size, release date, or the presence of test-time reasoning. However, extending the context of prior messages substantially increases rates of delusion-linked behaviors, providing evidence for the importance of context in LLM safety evaluation. For example, the rate of failing to discourage self-harm when the user expresses suicidal ideation increases from 30.0% to 41.1% when an additional 350 messages are prepended to the conversation history. All model families (e.g., GPT, Claude) exhibit substantial rates of delusion-linked behaviors. Within families, later, larger, or higher-reasoning models are not uniformly better across all behavior categories. Our results raise concerns regarding the potential psychological impact of LLMs and the need for more rigorous studies of real-world human-AI interaction.
Large language models (LLMs) perform table-centric prediction through in-context learning, making demonstration selection critical to performance. Existing retrieval methods prioritize similarity to the query, but similar demonstrations often reinforce the model's likely prediction rather than reveal the distinctions needed for difficult decisions. We propose EdgeLM, a retrieval framework that instead selects edge evidence, demonstrations that are both relevant to the query and informative about the decision boundary. EdgeLM retrieves two complementary forms of edge evidence by selecting data edges, nearby examples with different ground-truth labels, and model edges, similar examples previously misclassified by the deployed model. EdgeLM requires neither model retraining nor task-specific engineering. Across five data wrangling tasks, fifteen datasets, and five open-weight and proprietary LLMs, EdgeLM consistently achieves the best or near-best performance in every setting, while ablations show that the two forms of edge evidence provide complementary benefits. Our code and datasets are publicly available at https://github.com/soroushomidvar/EdgeLM.
展开完整摘要收起摘要↓
Large language models (LLMs) perform table-centric prediction through in-context learning, making demonstration selection critical to performance. Existing retrieval methods prioritize similarity to the query, but similar demonstrations often reinforce the model's likely prediction rather than reveal the distinctions needed for difficult decisions. We propose EdgeLM, a retrieval framework that instead selects edge evidence, demonstrations that are both relevant to the query and informative about the decision boundary. EdgeLM retrieves two complementary forms of edge evidence by selecting data edges, nearby examples with different ground-truth labels, and model edges, similar examples previously misclassified by the deployed model. EdgeLM requires neither model retraining nor task-specific engineering. Across five data wrangling tasks, fifteen datasets, and five open-weight and proprietary LLMs, EdgeLM consistently achieves the best or near-best performance in every setting, while ablations show that the two forms of edge evidence provide complementary benefits. Our code and datasets are publicly available at https://github.com/soroushomidvar/EdgeLM.
Long context reasoning in large language models (LLMs) is usually constrained by the fact that a single inference trajectory has to simultaneously explore the context, store intermediate state, verify evidence, and produce the final answer. This becomes particularly difficult in tasks that require extraction, counting, ordering, or multi-hop reasoning, where an early mistake can propagate until the final response. In this work, we propose Chained Recursive Language Models (Chained RLM), an inference-time architecture, in which the same underlying model is called repeatedly as a sequence of fresh reasoning roots. Each root receives the original problem and context, but does not inherit the full conversational history. Instead, it receives a compact plain-text summary, a plain-text blackboard, and some durable task-specific artifacts written by predecessor roots. The motivation is to manage the context by chopping into partial tasks rather than one large inference response; in each staged computation, intermediate artifacts can be inspected, corrected, and extended by a later fresh inference by the same model. We describe the system model, handoff mechanism, artifact workspace, and evaluation protocol for this system. We study when fresh-context artifact continuation gives a measurable gain in accuracy over direct LLM answering even with recursive tool-calling.
展开完整摘要收起摘要↓
Long context reasoning in large language models (LLMs) is usually constrained by the fact that a single inference trajectory has to simultaneously explore the context, store intermediate state, verify evidence, and produce the final answer. This becomes particularly difficult in tasks that require extraction, counting, ordering, or multi-hop reasoning, where an early mistake can propagate until the final response. In this work, we propose Chained Recursive Language Models (Chained RLM), an inference-time architecture, in which the same underlying model is called repeatedly as a sequence of fresh reasoning roots. Each root receives the original problem and context, but does not inherit the full conversational history. Instead, it receives a compact plain-text summary, a plain-text blackboard, and some durable task-specific artifacts written by predecessor roots. The motivation is to manage the context by chopping into partial tasks rather than one large inference response; in each staged computation, intermediate artifacts can be inspected, corrected, and extended by a later fresh inference by the same model. We describe the system model, handoff mechanism, artifact workspace, and evaluation protocol for this system. We study when fresh-context artifact continuation gives a measurable gain in accuracy over direct LLM answering even with recursive tool-calling.
作者Byoungjae Min, Kennedy Edemacu, Sae-Hong Cho, Yoonhyuk Choi, Beakcheol Jang, Jong Wook Kim
Large language models (LLMs) are often asked whether something is absent from a record, list, or retrieved context. Yet non-observation licenses a negative answer only when evidence completely covers the query scope; otherwise, the answer should remain unknown. We call this completeness-sensitive negative reasoning. We introduce CROWN-QA, comprising CROWN-Synth, a controlled paired core that fixes the question and observed facts while varying only query-relative coverage, and CROWN-Real, a real-document contrast-set evaluation with controlled coverage variants. Across three LLM families, models show unstable closure judgments and substantial over-closure, failing to reliably distinguish a justified negative answer (Certified-Negative) from insufficient evidence (Unknown). The dominant CROWN-Synth failure is asymmetric: models often recognize implicitly complete evidence yet treat implicitly partial evidence as query-covering. Prompting redistributes errors between over- and under-closure rather than consistently resolving them. Structured certificate elicitation traces many errors to evidence-coverage mischaracterization. CROWN-Real shows that the core partial-coverage asymmetry persists on real-document content, while its strength and the balance between over- and under-closure vary by model, prompt, and source.
展开完整摘要收起摘要↓
Large language models (LLMs) are often asked whether something is absent from a record, list, or retrieved context. Yet non-observation licenses a negative answer only when evidence completely covers the query scope; otherwise, the answer should remain unknown. We call this completeness-sensitive negative reasoning. We introduce CROWN-QA, comprising CROWN-Synth, a controlled paired core that fixes the question and observed facts while varying only query-relative coverage, and CROWN-Real, a real-document contrast-set evaluation with controlled coverage variants. Across three LLM families, models show unstable closure judgments and substantial over-closure, failing to reliably distinguish a justified negative answer (Certified-Negative) from insufficient evidence (Unknown). The dominant CROWN-Synth failure is asymmetric: models often recognize implicitly complete evidence yet treat implicitly partial evidence as query-covering. Prompting redistributes errors between over- and under-closure rather than consistently resolving them. Structured certificate elicitation traces many errors to evidence-coverage mischaracterization. CROWN-Real shows that the core partial-coverage asymmetry persists on real-document content, while its strength and the balance between over- and under-closure vary by model, prompt, and source.
Multimodal large language models (MLLMs) achieve strong performance across diverse vision-language tasks, but their efficiency is limited by the cost of processing numerous visual tokens. Visual token pruning can reduce this cost, but requires accurate token importance estimates. Recent studies have demonstrated that text-to-vision attention from middle language model layers can effectively guide visual token pruning, typically using attention from a predefined middle layer to select the visual tokens to retain. Two problems therefore remain. First, our analysis shows that the layer whose attention is most responsive to the question varies substantially across samples, making a fixed layer suboptimal. Second, obtaining attention from the appropriate middle layer requires processing numerous visual tokens through several language model layers, by which point considerable computation has already been spent. To address both problems, we propose Middle-layer Attention Prediction (MAP), which uses Question Contrastive Teacher Selection to identify a sample-specific teacher layer by contrasting attention under the original and reference questions, and distills attention from the selected layer into a lightweight predictor that estimates visual token importance from multi-modal input features. During inference, MAP combines the predicted importance scores with a diversity criterion to prune visual tokens before the first language model layer. Thus, MAP requires no attention maps for pruning and remains compatible with existing inference acceleration techniques. Across ten benchmarks on LLaVA-NeXT-7B, MAP retains 97.5% of the unpruned model performance with only 5.56% of the visual tokens, yielding a 3.09x end-to-end speedup.
展开完整摘要收起摘要↓
Multimodal large language models (MLLMs) achieve strong performance across diverse vision-language tasks, but their efficiency is limited by the cost of processing numerous visual tokens. Visual token pruning can reduce this cost, but requires accurate token importance estimates. Recent studies have demonstrated that text-to-vision attention from middle language model layers can effectively guide visual token pruning, typically using attention from a predefined middle layer to select the visual tokens to retain. Two problems therefore remain. First, our analysis shows that the layer whose attention is most responsive to the question varies substantially across samples, making a fixed layer suboptimal. Second, obtaining attention from the appropriate middle layer requires processing numerous visual tokens through several language model layers, by which point considerable computation has already been spent. To address both problems, we propose Middle-layer Attention Prediction (MAP), which uses Question Contrastive Teacher Selection to identify a sample-specific teacher layer by contrasting attention under the original and reference questions, and distills attention from the selected layer into a lightweight predictor that estimates visual token importance from multi-modal input features. During inference, MAP combines the predicted importance scores with a diversity criterion to prune visual tokens before the first language model layer. Thus, MAP requires no attention maps for pruning and remains compatible with existing inference acceleration techniques. Across ten benchmarks on LLaVA-NeXT-7B, MAP retains 97.5% of the unpruned model performance with only 5.56% of the visual tokens, yielding a 3.09x end-to-end speedup.
作者Kishor Datta Gupta, Md. Mahfuzur Rahman, Fahad Rahman, Ahmed Rafi Hasan, Faysal Mehrab Chowdhury, Mohd Ariful Haque, Roy George
Edge platforms used for aerial observation must interpret aircraft imagery under limited memory, limited compute, and intermittent connectivity. This setting is difficult for standard RGB-only recognition models and general-purpose vision-language models, especially when calibrated thermal and LiDAR aircraft data are unavailable. We present TriCLE, an application-oriented tri-modal vision-language system for aircraft taxonomic grouping under edge constraints. From a single RGB aircraft image, TriCLE generates a structure-preserving FLIR-style thermal view and a pseudo-LiDAR depth projection, then fuses the aligned views with task instructions in a compact Qwen3-VL backbone. The model is aligned to an expert aircraft taxonomy based on propulsion, airframe family, size, design era, and configuration, so its outputs reflect engineering-relevant similarity rather than only surface appearance. We evaluate supervised fine-tuning, rotation-preserving SFT, and three policy-alignment strategies: GRPO, GSPO, and DAPO. Sequence-level GSPO gives the strongest validation performance, reaching 88.33% validation accuracy and 0.91 weighted F1 on valid aircraft outputs. On a held-out aircraft test partition, GSPO achieves 78.00% accuracy and 0.793 weighted F1 while preserving 94.00% parseable output formatting. After 4-bit quantization and attention-memory optimization, the aligned 4B model fits an 8GB deployment target and processes each tri-modal triplet in 1.48 seconds. These results support TriCLE as a practical prototype for interpretable, edge-feasible aircraft grouping, while emphasizing the need for further validation on real aligned thermal and LiDAR sensor streams.
展开完整摘要收起摘要↓
Edge platforms used for aerial observation must interpret aircraft imagery under limited memory, limited compute, and intermittent connectivity. This setting is difficult for standard RGB-only recognition models and general-purpose vision-language models, especially when calibrated thermal and LiDAR aircraft data are unavailable. We present TriCLE, an application-oriented tri-modal vision-language system for aircraft taxonomic grouping under edge constraints. From a single RGB aircraft image, TriCLE generates a structure-preserving FLIR-style thermal view and a pseudo-LiDAR depth projection, then fuses the aligned views with task instructions in a compact Qwen3-VL backbone. The model is aligned to an expert aircraft taxonomy based on propulsion, airframe family, size, design era, and configuration, so its outputs reflect engineering-relevant similarity rather than only surface appearance. We evaluate supervised fine-tuning, rotation-preserving SFT, and three policy-alignment strategies: GRPO, GSPO, and DAPO. Sequence-level GSPO gives the strongest validation performance, reaching 88.33% validation accuracy and 0.91 weighted F1 on valid aircraft outputs. On a held-out aircraft test partition, GSPO achieves 78.00% accuracy and 0.793 weighted F1 while preserving 94.00% parseable output formatting. After 4-bit quantization and attention-memory optimization, the aligned 4B model fits an 8GB deployment target and processes each tri-modal triplet in 1.48 seconds. These results support TriCLE as a practical prototype for interpretable, edge-feasible aircraft grouping, while emphasizing the need for further validation on real aligned thermal and LiDAR sensor streams.
作者Reza Ahmari, Ahmad Mohammadi, Vahid Hemmati, Nicholas Edmond, Hossein Z. Saghazadeh, Olusola Odeyomi, Parham Kebria, Abdollah Homaifar
Vision-based guidance of unmanned aerial vehicles (UAVs) toward unmanned ground vehicles (UGVs) supports cooperative aerial--ground robotics, but reliable continuous yaw estimation from onboard vision remains challenging because of sensing uncertainty, limited computation, and the need for interpretable control. Existing deep-learning and geometric-reconstruction approaches often require large datasets, external localization, or complex modeling assumptions, reducing transparency and deployment suitability on resource-constrained platforms. We present an interpretable fuzzy-inference framework that generates continuous yaw commands from low-dimensional features extracted from YOLO boxes: target centroid location, area, and aspect ratio. No explicit geometric modeling is required. A Mamdani fuzzy system serves as an interpretable baseline using a shoulder--triangle--shoulder input partition. It is followed by a first-order Takagi--Sugeno model with three antecedent membership terms per input, whose parameters are derived from training-set quantiles, yielding a compact 27-rule structure. Evaluation uses 6{,}169 labeled samples from a VICON motion-capture environment. Across five randomized train--test splits, the Takagi--Sugeno model achieves a test-set mean absolute error of $0.140^\circ \pm 0.003^\circ$, a root mean squared error of $0.200^\circ \pm 0.008^\circ$, and a maximum absolute error of $1.254^\circ \pm 0.121^\circ$. Within-threshold accuracies are $99.676% \pm 0.270%$ for $\pm1^\circ$ and $100.000% \pm 0.000%$ for both $\pm3^\circ$ and $\pm5^\circ$. Directional consistency between image-plane horizontal displacement and predicted yaw sign reaches $90.254% \pm 0.612%$. These results show that the framework is transparent, data-efficient, computationally lightweight, and suitable for real-time vision-based UAV guidance toward mobile ground targets.
展开完整摘要收起摘要↓
Vision-based guidance of unmanned aerial vehicles (UAVs) toward unmanned ground vehicles (UGVs) supports cooperative aerial--ground robotics, but reliable continuous yaw estimation from onboard vision remains challenging because of sensing uncertainty, limited computation, and the need for interpretable control. Existing deep-learning and geometric-reconstruction approaches often require large datasets, external localization, or complex modeling assumptions, reducing transparency and deployment suitability on resource-constrained platforms. We present an interpretable fuzzy-inference framework that generates continuous yaw commands from low-dimensional features extracted from YOLO boxes: target centroid location, area, and aspect ratio. No explicit geometric modeling is required. A Mamdani fuzzy system serves as an interpretable baseline using a shoulder--triangle--shoulder input partition. It is followed by a first-order Takagi--Sugeno model with three antecedent membership terms per input, whose parameters are derived from training-set quantiles, yielding a compact 27-rule structure. Evaluation uses 6{,}169 labeled samples from a VICON motion-capture environment. Across five randomized train--test splits, the Takagi--Sugeno model achieves a test-set mean absolute error of $0.140^\circ \pm 0.003^\circ$, a root mean squared error of $0.200^\circ \pm 0.008^\circ$, and a maximum absolute error of $1.254^\circ \pm 0.121^\circ$. Within-threshold accuracies are $99.676% \pm 0.270%$ for $\pm1^\circ$ and $100.000% \pm 0.000%$ for both $\pm3^\circ$ and $\pm5^\circ$. Directional consistency between image-plane horizontal displacement and predicted yaw sign reaches $90.254% \pm 0.612%$. These results show that the framework is transparent, data-efficient, computationally lightweight, and suitable for real-time vision-based UAV guidance toward mobile ground targets.
Historical films suffer from co-occurring visual and audio degradations---blur, noise, flicker, hiss, clipping, and dropout---yet existing methods restore each modality independently, leaving quality gaps and cross-modal inconsistency. We present OmniVR, the first joint audio-video generative restoration model. Built upon a 22B-parameter audio-video generation backbone, OmniVR formulates restoration as conditional generation within a unified multimodal DiT: the low-quality video and audio are encoded as latent conditions, combined with a fixed restoration prompt, and jointly denoised to recover visual structure, temporal motion, and acoustic detail under one coordinated objective. Three key designs enable this adaptation: (1) a joint audio-video degradation pipeline that simulates real old-film characteristics from Internet-collected data; (2) an architecture-preserving text-to-audio-video (T2AV) to audio-video-to-audio-video (AV2AV) transition with prompt annealing that maximally retains the generative prior; and (3) first-frame image-to-video (I2V) anchoring with loss reweighting and waveform supervision for long-video extrapolation and audio fidelity. We also propose OmniVRBench, the first benchmark that evaluates audio-video restoration across visual quality, audio quality, temporal consistency, and audio-visual synchrony on 200 real historical clips. OmniVR surpasses all prior methods on all six visual metrics, achieves the best audio quality, and produces natural colorization---the first method to jointly address all three aspects. Code and weights will be publicly released. Project Page: https://xin1u.github.io/OminiVR_PAGE/
展开完整摘要收起摘要↓
Historical films suffer from co-occurring visual and audio degradations---blur, noise, flicker, hiss, clipping, and dropout---yet existing methods restore each modality independently, leaving quality gaps and cross-modal inconsistency. We present OmniVR, the first joint audio-video generative restoration model. Built upon a 22B-parameter audio-video generation backbone, OmniVR formulates restoration as conditional generation within a unified multimodal DiT: the low-quality video and audio are encoded as latent conditions, combined with a fixed restoration prompt, and jointly denoised to recover visual structure, temporal motion, and acoustic detail under one coordinated objective. Three key designs enable this adaptation: (1) a joint audio-video degradation pipeline that simulates real old-film characteristics from Internet-collected data; (2) an architecture-preserving text-to-audio-video (T2AV) to audio-video-to-audio-video (AV2AV) transition with prompt annealing that maximally retains the generative prior; and (3) first-frame image-to-video (I2V) anchoring with loss reweighting and waveform supervision for long-video extrapolation and audio fidelity. We also propose OmniVRBench, the first benchmark that evaluates audio-video restoration across visual quality, audio quality, temporal consistency, and audio-visual synchrony on 200 real historical clips. OmniVR surpasses all prior methods on all six visual metrics, achieves the best audio quality, and produces natural colorization---the first method to jointly address all three aspects. Code and weights will be publicly released. Project Page: https://xin1u.github.io/OminiVR_PAGE/
Existing reference-free methods for evaluating music perceptual quality alleviate the need for paired noisy-clean data, but they still rely on a background set, which is used to compute aggregated statistics of clean audio samples. In this work, we propose a novel approach that eliminates this requirement, achieving background-set-free and reference-free quality estimation using only a pre-trained Flow Matching backbone. We demonstrate that unconditional Flow Matching inversion via simple Euler integration is sufficient to detect various artificial distortions and accurately rank music generation models against human perceptual judgments. We introduce InvFlowFD, which performs flow inversion and compares a group of inverted samples to the prior distribution. We evaluate our method against prior work, quantitatively and with a thorough human study. Results suggest that InvFlowFD is highly correlated with human perception of sound distortions, as well as generative models' quality, while being more flexible and less restrictive than existing metrics.
展开完整摘要收起摘要↓
Existing reference-free methods for evaluating music perceptual quality alleviate the need for paired noisy-clean data, but they still rely on a background set, which is used to compute aggregated statistics of clean audio samples. In this work, we propose a novel approach that eliminates this requirement, achieving background-set-free and reference-free quality estimation using only a pre-trained Flow Matching backbone. We demonstrate that unconditional Flow Matching inversion via simple Euler integration is sufficient to detect various artificial distortions and accurately rank music generation models against human perceptual judgments. We introduce InvFlowFD, which performs flow inversion and compares a group of inverted samples to the prior distribution. We evaluate our method against prior work, quantitatively and with a thorough human study. Results suggest that InvFlowFD is highly correlated with human perception of sound distortions, as well as generative models' quality, while being more flexible and less restrictive than existing metrics.
作者Maksymilian Wojnar, Krzysztof Rusek, Katarzyna Kosek-Szott, Szymon Szott
Wi-Fi networks are moving beyond random channel access toward tightly coordinated operation across access points (APs), a shift reflected in Wi-Fi 8's multi-AP coordination (MAPC). However, the current MAPC specification restricts cooperation to AP pairs, fundamentally limiting the gains achievable in dense deployments and calling for scalable, network-wide coordination in beyond Wi-Fi 8 systems. We target coordinated spatial reuse (Co-SR), where APs transmit concurrently at reduced power. Effective Co-SR demands joint selection and configuration of AP-station transmissions, yet existing approaches simply do not scale: they rely on heavy signaling, slow convergence, unrealistic assumptions, and often require computation time that explodes with network size. We introduce FM4WiFi, a generative ML pipeline that addresses these limitations by producing high-quality Co-SR configurations in a single inference step. FM4WiFi integrates (i) an autoencoder that learns compact latent representations of network states, (ii) a flow-matching generative model that synthesizes feasible Co-SR configurations (including rate control, absent from prior work), and (iii) a surrogate rate predictor that allows rapid, large-scale Co-SR candidate evaluation without dependence on a live system or digital twin. Across extensive evaluations (including experimental validation), FM4WiFi matches or exceeds state-of-the-art baselines at medium-to-large scales and scales to 30+ APs with sub-second inference. Extensive ablation studies validate each modeling and optimization choice.
展开完整摘要收起摘要↓
Wi-Fi networks are moving beyond random channel access toward tightly coordinated operation across access points (APs), a shift reflected in Wi-Fi 8's multi-AP coordination (MAPC). However, the current MAPC specification restricts cooperation to AP pairs, fundamentally limiting the gains achievable in dense deployments and calling for scalable, network-wide coordination in beyond Wi-Fi 8 systems. We target coordinated spatial reuse (Co-SR), where APs transmit concurrently at reduced power. Effective Co-SR demands joint selection and configuration of AP-station transmissions, yet existing approaches simply do not scale: they rely on heavy signaling, slow convergence, unrealistic assumptions, and often require computation time that explodes with network size. We introduce FM4WiFi, a generative ML pipeline that addresses these limitations by producing high-quality Co-SR configurations in a single inference step. FM4WiFi integrates (i) an autoencoder that learns compact latent representations of network states, (ii) a flow-matching generative model that synthesizes feasible Co-SR configurations (including rate control, absent from prior work), and (iii) a surrogate rate predictor that allows rapid, large-scale Co-SR candidate evaluation without dependence on a live system or digital twin. Across extensive evaluations (including experimental validation), FM4WiFi matches or exceeds state-of-the-art baselines at medium-to-large scales and scales to 30+ APs with sub-second inference. Extensive ablation studies validate each modeling and optimization choice.
作者Shihao Weng, Yang Feng, Xiaofei Xie, Jiongchi Yu
Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous encounters. In practice, user requests are often underspecified: they describe the desired outcome without fully specifying acceptable behavior. An injection can exploit this ambiguity, causing the agent to complete the task in a way the user would reject. As the user's expectations become clearer through concrete cases, a defense should learn from each encounter and apply what it learns to the next. Inspired by adaptive immunity, we propose AgentAntibody, which equips LLM agents with a self-evolving immune system against prompt injection. AgentAntibody represents its evolving understanding of the user's security boundary as a persistent library of antibodies. At runtime, the library recognizes threats to this boundary and mounts corresponding immune responses. Across encounters, it evolves to strengthen the agent's immunity to future attacks. Extensive experiments across three benchmarks and four backbone LLMs show that, by learning the user's boundary through experience, AgentAntibody outperforms existing defenses in preventing harmful actions while preserving legitimate task completion, even when the harmful and legitimate actions are both compatible with the stated task.
展开完整摘要收起摘要↓
Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous encounters. In practice, user requests are often underspecified: they describe the desired outcome without fully specifying acceptable behavior. An injection can exploit this ambiguity, causing the agent to complete the task in a way the user would reject. As the user's expectations become clearer through concrete cases, a defense should learn from each encounter and apply what it learns to the next. Inspired by adaptive immunity, we propose AgentAntibody, which equips LLM agents with a self-evolving immune system against prompt injection. AgentAntibody represents its evolving understanding of the user's security boundary as a persistent library of antibodies. At runtime, the library recognizes threats to this boundary and mounts corresponding immune responses. Across encounters, it evolves to strengthen the agent's immunity to future attacks. Extensive experiments across three benchmarks and four backbone LLMs show that, by learning the user's boundary through experience, AgentAntibody outperforms existing defenses in preventing harmful actions while preserving legitimate task completion, even when the harmful and legitimate actions are both compatible with the stated task.
作者Lucas Gouveia Omena Lopes, Thales Miranda de Almeida Vieira, Eduardo Toledo de Lima Junior, William Wagner Matos Lira
Open-World Learning (OWL) pipelines for oil well anomaly detection have recently been shown to combine autoencoder-based detection, multiclass classification, and Mahalanobis-based novelty detection on the public 3W dataset. These pipelines answer what happened, but they do not explain why the model believes it or what the operator should do next, and they do not put a human-readable name on the novelty clusters they discover. This paper evaluates a Large Language Model (LLM) agent layer placed downstream of the OWL pipeline, designed as a companion to the published upstream methods rather than a replacement. Using the Qwen3.5-397B-A17B Mixture-of-Experts model served via NVIDIA NIM, the agent receives structured sensor metrics and upstream classification or novelty assertions, and returns natural-language justifications, confidence-ranked critiques, and consolidated names for detected novelties. Across three studies spanning 989 real well-file segments from the 3W dataset, the agent achieved $35.1%$ top-1 / $63.9%$ top-3 (95% CI [56.9, 70.4]) classification on all nine classes, $71.7%$ top-2 validation [64.8, 77.6] with precision $0.91$ [0.84, 0.95] across 7 probed classes, and $89.7%$ novelty detection [87.0, 91.9] with stable cluster naming on 5 of 7 hidden classes. The agent is not a standalone classifier. Its role is to: (1) confirm upstream decisions when sensor evidence supports them, (2) justify decisions in sensor-grounded language operators can audit, (3) flag disagreement when upstream labels are implausible, and (4) name novelties so that clustered unlabeled events arrive at the engineer with a consolidated human-readable label. The goal is to close the explainability gap that currently blocks deployment of OWL pipelines in operational settings.
展开完整摘要收起摘要↓
Open-World Learning (OWL) pipelines for oil well anomaly detection have recently been shown to combine autoencoder-based detection, multiclass classification, and Mahalanobis-based novelty detection on the public 3W dataset. These pipelines answer what happened, but they do not explain why the model believes it or what the operator should do next, and they do not put a human-readable name on the novelty clusters they discover. This paper evaluates a Large Language Model (LLM) agent layer placed downstream of the OWL pipeline, designed as a companion to the published upstream methods rather than a replacement. Using the Qwen3.5-397B-A17B Mixture-of-Experts model served via NVIDIA NIM, the agent receives structured sensor metrics and upstream classification or novelty assertions, and returns natural-language justifications, confidence-ranked critiques, and consolidated names for detected novelties. Across three studies spanning 989 real well-file segments from the 3W dataset, the agent achieved $35.1%$ top-1 / $63.9%$ top-3 (95% CI [56.9, 70.4]) classification on all nine classes, $71.7%$ top-2 validation [64.8, 77.6] with precision $0.91$ [0.84, 0.95] across 7 probed classes, and $89.7%$ novelty detection [87.0, 91.9] with stable cluster naming on 5 of 7 hidden classes. The agent is not a standalone classifier. Its role is to: (1) confirm upstream decisions when sensor evidence supports them, (2) justify decisions in sensor-grounded language operators can audit, (3) flag disagreement when upstream labels are implausible, and (4) name novelties so that clustered unlabeled events arrive at the engineer with a consolidated human-readable label. The goal is to close the explainability gap that currently blocks deployment of OWL pipelines in operational settings.
High-resolution images and long videos provide vision-language models with rich context for multimodal reasoning and fine-grained perception, but the resulting long visual token sequences make large language model-side computation and memory costly. Existing visual token reducers often operate at prescribed rates, while recent methods adapt token counts across inputs using method-specific learned thresholds or importance predictors. We introduce RUTA, a principled Rate-Utility Token Allocation method that performs pre-LLM reduction by jointly learning which tokens to retain and how many to allocate to each image-query pair. RUTA constructs query-conditioned candidate tokens and predicts a retention probability for each candidate. During training, these probabilities parameterize independent Bernoulli gates, while their sum provides a differentiable training-time estimate of the token count for each pair. Retained tokens serve as anchors that aggregate information from non-retained tokens according to semantic affinity and spatial proximity. RUTA is optimized with a penalized rate-utility objective that balances downstream task loss against expected token usage. Averaged across five benchmarks and measured relative to each backbone's full-token baseline, RUTA uses only $2.0%$ and $4.2%$ of visual tokens while preserving $88.2%$ and $94.4%$ of task performance on LLaVA-NeXT-7B and Qwen3-VL-8B, respectively.
展开完整摘要收起摘要↓
High-resolution images and long videos provide vision-language models with rich context for multimodal reasoning and fine-grained perception, but the resulting long visual token sequences make large language model-side computation and memory costly. Existing visual token reducers often operate at prescribed rates, while recent methods adapt token counts across inputs using method-specific learned thresholds or importance predictors. We introduce RUTA, a principled Rate-Utility Token Allocation method that performs pre-LLM reduction by jointly learning which tokens to retain and how many to allocate to each image-query pair. RUTA constructs query-conditioned candidate tokens and predicts a retention probability for each candidate. During training, these probabilities parameterize independent Bernoulli gates, while their sum provides a differentiable training-time estimate of the token count for each pair. Retained tokens serve as anchors that aggregate information from non-retained tokens according to semantic affinity and spatial proximity. RUTA is optimized with a penalized rate-utility objective that balances downstream task loss against expected token usage. Averaged across five benchmarks and measured relative to each backbone's full-token baseline, RUTA uses only $2.0%$ and $4.2%$ of visual tokens while preserving $88.2%$ and $94.4%$ of task performance on LLaVA-NeXT-7B and Qwen3-VL-8B, respectively.
Long-horizon agents increasingly use persistent memory and tools to take actions with external side effects. A central failure mode is premature commitment: an agent acts before resolving whether its memory grounding is stale, conflicting, incomplete, or corrupted. We formalize this problem as safe commitment under memory uncertainty and introduce SafeCommit, a risk controlled layer between agent reasoning and external execution. The layer constructs a calibrated set of plausible latent worlds from memory, observations, tool outputs, provenance, and policy constraints. It permits a side effectful action only when a conformal action certificate shows that the action is safe in every retained world. Otherwise, it selects a low-side-effect probe that targets the worlds blocking certification, or returns a conservative fallback. Under calibrated world coverage, the probability of an unsafe certified commit is at most the target level α; with imperfect world proposal, the bound separates calibration and representation error. A dependency-free controlled simulator illustrates the safety-utility tradeoff and reproduces all reported results with one command. The goal is to offer a concrete approach for deciding not only what an agent should do, but when the available evidence is sufficient to safely do it.
展开完整摘要收起摘要↓
Long-horizon agents increasingly use persistent memory and tools to take actions with external side effects. A central failure mode is premature commitment: an agent acts before resolving whether its memory grounding is stale, conflicting, incomplete, or corrupted. We formalize this problem as safe commitment under memory uncertainty and introduce SafeCommit, a risk controlled layer between agent reasoning and external execution. The layer constructs a calibrated set of plausible latent worlds from memory, observations, tool outputs, provenance, and policy constraints. It permits a side effectful action only when a conformal action certificate shows that the action is safe in every retained world. Otherwise, it selects a low-side-effect probe that targets the worlds blocking certification, or returns a conservative fallback. Under calibrated world coverage, the probability of an unsafe certified commit is at most the target level α; with imperfect world proposal, the bound separates calibration and representation error. A dependency-free controlled simulator illustrates the safety-utility tradeoff and reproduces all reported results with one command. The goal is to offer a concrete approach for deciding not only what an agent should do, but when the available evidence is sufficient to safely do it.
Evaluations of LLM planning agents largely ask whether a task succeeds or a declared plan is followed. In strategic cyber-physical systems, a stronger question is whether the planning architecture remains appropriate after autonomous participants respond and physics constrains the outcome. We introduce a controlled, physics-grounded benchmark built around planning-induced control trajectories: the ordered planning operations and directives through which an execution architecture acts on other agents and the physical process. It implements predefined, sequential, hierarchical, and search executors in a smart-grid demand-response system with 40 heterogeneous prosumers and an independently simulated radial feeder. The LLM is bounded to typed policy declaration and short operator messages, while schedule construction, prosumer dynamics, and power flow remain explicit code. The protocol uses paired forced-mode counterfactuals, common random response draws, and event-level deadline feasibility. Three properties follow. Architecture materially changes outcomes: forced search is the oracle in all five baseline seeds. Execution fidelity needs more than mode agreement: objective substitution holds agreement at 1.0 while increasing voltage shortfall by 2.68x. A 144-scenario, 576-episode bank has feasible oracles from three of the four architectures. A prespecified stress-held-out ridge has mean regret 90.7 (95% interval [73.8, 108.6]) and no detectable value over fixed sequential; applying known deadline feasibility before quality prediction cuts regret to 29.0 and improves over fixed sequential by 61.1. An all-feasible ablation does not beat fixed search, localising the remaining challenge to within-feasible quality selection. A five-model extension separates stress-conditioned, state-blind, and invariant declarers; latency tails show that live feasibility should be treated probabilistically.
展开完整摘要收起摘要↓
Evaluations of LLM planning agents largely ask whether a task succeeds or a declared plan is followed. In strategic cyber-physical systems, a stronger question is whether the planning architecture remains appropriate after autonomous participants respond and physics constrains the outcome. We introduce a controlled, physics-grounded benchmark built around planning-induced control trajectories: the ordered planning operations and directives through which an execution architecture acts on other agents and the physical process. It implements predefined, sequential, hierarchical, and search executors in a smart-grid demand-response system with 40 heterogeneous prosumers and an independently simulated radial feeder. The LLM is bounded to typed policy declaration and short operator messages, while schedule construction, prosumer dynamics, and power flow remain explicit code. The protocol uses paired forced-mode counterfactuals, common random response draws, and event-level deadline feasibility. Three properties follow. Architecture materially changes outcomes: forced search is the oracle in all five baseline seeds. Execution fidelity needs more than mode agreement: objective substitution holds agreement at 1.0 while increasing voltage shortfall by 2.68x. A 144-scenario, 576-episode bank has feasible oracles from three of the four architectures. A prespecified stress-held-out ridge has mean regret 90.7 (95% interval [73.8, 108.6]) and no detectable value over fixed sequential; applying known deadline feasibility before quality prediction cuts regret to 29.0 and improves over fixed sequential by 61.1. An all-feasible ablation does not beat fixed search, localising the remaining challenge to within-feasible quality selection. A five-model extension separates stress-conditioned, state-blind, and invariant declarers; latency tails show that live feasibility should be treated probabilistically.
Automatically generating professional multimodal reports comprising both textual analysis and visual charts from structured tabular data is a critical challenge in data intelligence. Existing methods suffer from fixed linear pipelines and isolated subtask processing, which hinder joint optimization of factual accuracy, visual quality, and narrative coherence. To address these issues, this paper proposes MCTS-Report, a Monte Carlo Tree Search (MCTS)-driven framework that formulates multimodal table-to-report generation as a progressive construction process over a structured search space. The core idea is to decompose report generation into atomic actions, including chapter planning, visualization task identification, chart generation, insight organization, and narrative refinement, each executed by an LLM based on dynamic reasoning conditioned on the current report state. We use an LLM to generate step-by-step reasoning and actions during MCTS, storing the reasoning trajectory in each node for context-aware, coherent report construction. To guide the search, we design a multi-dimensional reward function that jointly evaluates numerical fact consistency (via SQL), chart quality, chart-text alignment, and structural completeness, while incorporating a diversity penalty to suppress repeated charts and a precondition check to prune invalid actions. We also construct MMRBench, a comprehensive benchmark comprising real-world tables from six domains, paired with expert-refined reference report structures and verifiable key insights. Experiments on MMRBench demonstrate that MCTS-Report significantly outperforms strong baselines across structural completeness, numerical accuracy, chart-text alignment, and insight novelty, achieving a 77.9 overall score.
展开完整摘要收起摘要↓
Automatically generating professional multimodal reports comprising both textual analysis and visual charts from structured tabular data is a critical challenge in data intelligence. Existing methods suffer from fixed linear pipelines and isolated subtask processing, which hinder joint optimization of factual accuracy, visual quality, and narrative coherence. To address these issues, this paper proposes MCTS-Report, a Monte Carlo Tree Search (MCTS)-driven framework that formulates multimodal table-to-report generation as a progressive construction process over a structured search space. The core idea is to decompose report generation into atomic actions, including chapter planning, visualization task identification, chart generation, insight organization, and narrative refinement, each executed by an LLM based on dynamic reasoning conditioned on the current report state. We use an LLM to generate step-by-step reasoning and actions during MCTS, storing the reasoning trajectory in each node for context-aware, coherent report construction. To guide the search, we design a multi-dimensional reward function that jointly evaluates numerical fact consistency (via SQL), chart quality, chart-text alignment, and structural completeness, while incorporating a diversity penalty to suppress repeated charts and a precondition check to prune invalid actions. We also construct MMRBench, a comprehensive benchmark comprising real-world tables from six domains, paired with expert-refined reference report structures and verifiable key insights. Experiments on MMRBench demonstrate that MCTS-Report significantly outperforms strong baselines across structural completeness, numerical accuracy, chart-text alignment, and insight novelty, achieving a 77.9 overall score.
Agentic AI is increasingly used to coordinate planning, implementation, review, and testing in software development, yet it often offers limited transparency into its decisions and interactions. Many such systems also assume that users can effectively guide the AI's decisions and validate its outputs. This assumption poses a particular challenge for novices, who must simultaneously learn how agentic AI works, how to collaborate with it effectively, and how to evaluate its outputs critically. To address this challenge, we present AgentForge, an immersive learning system in which novices take on one of four software-engineering roles: Task Planner, Patch Author, Code Reviewer, or Test Runner, within a multi-agent code-repair workflow. In each practice session, the novices perform their chosen role while AI agents perform the remaining three. Through role-based scaffolding and metacognitive support, AgentForge clarifies role-specific responsibilities, makes agent coordination and intermediate artifacts visible, and encourages novices to monitor and evaluate their decisions. In a study with 37 novice developers, participants achieved high task-completion rates with AI-agent support. However, interaction demands differed significantly across practices: the Code Reviewer practice required more interaction turns, reroutes, and completion time ($p_{\mathrm{adj}} = .004$) and was perceived as the most challenging. Participants nevertheless reported significant gains in their understanding of software repair and agent collaboration ($p_{\mathrm{adj}} < .001$). These findings suggest that AgentForge can help novices develop practical software-engineering skills while learning to collaborate with agentic AI more critically and effectively.
展开完整摘要收起摘要↓
Agentic AI is increasingly used to coordinate planning, implementation, review, and testing in software development, yet it often offers limited transparency into its decisions and interactions. Many such systems also assume that users can effectively guide the AI's decisions and validate its outputs. This assumption poses a particular challenge for novices, who must simultaneously learn how agentic AI works, how to collaborate with it effectively, and how to evaluate its outputs critically. To address this challenge, we present AgentForge, an immersive learning system in which novices take on one of four software-engineering roles: Task Planner, Patch Author, Code Reviewer, or Test Runner, within a multi-agent code-repair workflow. In each practice session, the novices perform their chosen role while AI agents perform the remaining three. Through role-based scaffolding and metacognitive support, AgentForge clarifies role-specific responsibilities, makes agent coordination and intermediate artifacts visible, and encourages novices to monitor and evaluate their decisions. In a study with 37 novice developers, participants achieved high task-completion rates with AI-agent support. However, interaction demands differed significantly across practices: the Code Reviewer practice required more interaction turns, reroutes, and completion time ($p_{\mathrm{adj}} = .004$) and was perceived as the most challenging. Participants nevertheless reported significant gains in their understanding of software repair and agent collaboration ($p_{\mathrm{adj}} < .001$). These findings suggest that AgentForge can help novices develop practical software-engineering skills while learning to collaborate with agentic AI more critically and effectively.
作者Hadi Mohammadi, Tina Shahedi, Robert A. Bagheri, Mehdi Dastani, Masoume M. Raeissi
When people label text for sexism, they often disagree, and not because some of them are wrong: they genuinely perceive sexism differently. Most NLP systems discard this disagreement by collapsing it into a majority vote. We propose the Multi-Agent Perspectivist Preference Optimization (MAP-PO) framework to keep these different perspectives. On the EXIST 2024 dataset of labeled English and Spanish tweets, we first cluster annotators by their labeling behavior rather than their demographic attributes. We then fine-tune one Large Language Model agent per cluster to reproduce that cluster's annotation behavior, and coordinate the agents with preference optimization that combines individual and team-level rewards. We evaluate MAP-PO in four settings defined by two languages and two backbone language models, asking whether each agent reproduces the annotations of its own cluster and whether the agents together reproduce the majority label. Two findings hold in all four settings. First, without fine-tuning the agents behave almost identically, so cluster-specific training is necessary. Second, we show that training each agent only on the labels of its own cluster pushes the agents far beyond the clusters they should represent, while adding a shared team-level training signal consistently keeps each agent calibrated to its cluster.
展开完整摘要收起摘要↓
When people label text for sexism, they often disagree, and not because some of them are wrong: they genuinely perceive sexism differently. Most NLP systems discard this disagreement by collapsing it into a majority vote. We propose the Multi-Agent Perspectivist Preference Optimization (MAP-PO) framework to keep these different perspectives. On the EXIST 2024 dataset of labeled English and Spanish tweets, we first cluster annotators by their labeling behavior rather than their demographic attributes. We then fine-tune one Large Language Model agent per cluster to reproduce that cluster's annotation behavior, and coordinate the agents with preference optimization that combines individual and team-level rewards. We evaluate MAP-PO in four settings defined by two languages and two backbone language models, asking whether each agent reproduces the annotations of its own cluster and whether the agents together reproduce the majority label. Two findings hold in all four settings. First, without fine-tuning the agents behave almost identically, so cluster-specific training is necessary. Second, we show that training each agent only on the labels of its own cluster pushes the agents far beyond the clusters they should represent, while adding a shared team-level training signal consistently keeps each agent calibrated to its cluster.
作者Ben Wang, Kang Zhou, Lifan Guo, Feng Chen, Chi Zhang
Large language model (LLM) agents are increasingly used as personalized assistants in high-stakes domains such as financial advising, yet it remains unclear whether they can maintain and update an individualized user model over long horizons. Existing personalized-memory benchmarks primarily test factual retention or rely on weakly constrained model-generated trajectories, leaving event-driven preference adaptation underexplored. We introduce FinPerMA, an event-grounded benchmark that evaluates personalized memory against frozen longitudinal investor trajectories. Its generation pipeline combines deterministic, theory-informed impact rules, controlled LLM narration, and automated quality screening; a Post-Shock checkpoint isolates whether an agent has integrated a material event into its persistent user model. On 2,994 questions from 276 personas, seven frontier LLMs and up to seven memory configurations remain far from saturated: no full-context configuration exceeds approximately 0.47 overall accuracy or approximately 39% on multiple-choice questions. Attribution analysis shows that summary-based memory often preserves factual details while losing the preference signals needed for personalization; simple retrieval can therefore outperform purpose-built memory systems, with the gap widening after shocks.
展开完整摘要收起摘要↓
Large language model (LLM) agents are increasingly used as personalized assistants in high-stakes domains such as financial advising, yet it remains unclear whether they can maintain and update an individualized user model over long horizons. Existing personalized-memory benchmarks primarily test factual retention or rely on weakly constrained model-generated trajectories, leaving event-driven preference adaptation underexplored. We introduce FinPerMA, an event-grounded benchmark that evaluates personalized memory against frozen longitudinal investor trajectories. Its generation pipeline combines deterministic, theory-informed impact rules, controlled LLM narration, and automated quality screening; a Post-Shock checkpoint isolates whether an agent has integrated a material event into its persistent user model. On 2,994 questions from 276 personas, seven frontier LLMs and up to seven memory configurations remain far from saturated: no full-context configuration exceeds approximately 0.47 overall accuracy or approximately 39% on multiple-choice questions. Attribution analysis shows that summary-based memory often preserves factual details while losing the preference signals needed for personalization; simple retrieval can therefore outperform purpose-built memory systems, with the gap widening after shocks.
LLM agents are increasingly applied to open-ended everyday requests that span work, study, and life. These tasks are long-horizon, cross-environment, and multimodal, forcing the agent to preserve goals and constraints across many steps while navigating heterogeneous tools and attachments. While prior work has addressed individual failure modes such as goals drift, states loss, and context overflow, whether a single harness can manage them jointly and remain effective across backends has received less study. We present OneDayAgent, a long-horizon harness for autonomous agents. OneDayAgent turns an open-ended request into a managed execution process that decomposes tasks into bounded subtasks, maintains execution memory under context pressure, and verifies and repairs the final deliverable. We evaluate OneDayAgent on AgentIF-OneDay across 104 tasks. With the GLM-5.2 backend, OneDayAgent sets a new state of the art with an overall score of 0.821. The same harness runs across five backend LLMs from three model families, indicating the harness generalizes across backends without tuning, even as different models induce distinct execution styles under the same workflow.
展开完整摘要收起摘要↓
LLM agents are increasingly applied to open-ended everyday requests that span work, study, and life. These tasks are long-horizon, cross-environment, and multimodal, forcing the agent to preserve goals and constraints across many steps while navigating heterogeneous tools and attachments. While prior work has addressed individual failure modes such as goals drift, states loss, and context overflow, whether a single harness can manage them jointly and remain effective across backends has received less study. We present OneDayAgent, a long-horizon harness for autonomous agents. OneDayAgent turns an open-ended request into a managed execution process that decomposes tasks into bounded subtasks, maintains execution memory under context pressure, and verifies and repairs the final deliverable. We evaluate OneDayAgent on AgentIF-OneDay across 104 tasks. With the GLM-5.2 backend, OneDayAgent sets a new state of the art with an overall score of 0.821. The same harness runs across five backend LLMs from three model families, indicating the harness generalizes across backends without tuning, even as different models induce distinct execution styles under the same workflow.
作者Haiqiang Zhang, Yuanqing Lei, Wanting Li, Tao Zhang, Wenqi Jiang
Retrieval-augmented generation (RAG), which augments large language model (LLM) generation with information retrieved from databases, has become a widely used approach for knowledge-intensive applications. Modern RAG systems, however, expose many configuration choices, such as retrieval indexes, model selections, and how models invoke retrieval. Each configuration yields a different trade-off between answer quality and serving performance, making it challenging to choose the optimal setting for a specific application deployment. We present RAG-Stack, a framework for efficiently discovering quality-performance Pareto frontiers across diverse RAG applications and serving systems. RAG-Stack consists of RAG-PE, an iterative design-space exploration algorithm that selects the next RAG configuration to evaluate; RAG-IR, a workload abstraction for diverse RAG algorithms; and RAG-CM, a performance model that predicts the optimal deployment and serving performance on the given hardware. Together, these components allow RAG-Stack to search the joint algorithm-system configuration space without deploying every candidate and to transfer an existing Pareto frontier to a new serving system. Given the same number of optimization iterations across diverse datasets, the Pareto frontiers found by RAG-Stack cover 52.5% to 153.2% more of the normalized quality-performance space than those found by state-of-the-art configuration-search methods evaluated over the same RAG design space.
展开完整摘要收起摘要↓
Retrieval-augmented generation (RAG), which augments large language model (LLM) generation with information retrieved from databases, has become a widely used approach for knowledge-intensive applications. Modern RAG systems, however, expose many configuration choices, such as retrieval indexes, model selections, and how models invoke retrieval. Each configuration yields a different trade-off between answer quality and serving performance, making it challenging to choose the optimal setting for a specific application deployment. We present RAG-Stack, a framework for efficiently discovering quality-performance Pareto frontiers across diverse RAG applications and serving systems. RAG-Stack consists of RAG-PE, an iterative design-space exploration algorithm that selects the next RAG configuration to evaluate; RAG-IR, a workload abstraction for diverse RAG algorithms; and RAG-CM, a performance model that predicts the optimal deployment and serving performance on the given hardware. Together, these components allow RAG-Stack to search the joint algorithm-system configuration space without deploying every candidate and to transfer an existing Pareto frontier to a new serving system. Given the same number of optimization iterations across diverse datasets, the Pareto frontiers found by RAG-Stack cover 52.5% to 153.2% more of the normalized quality-performance space than those found by state-of-the-art configuration-search methods evaluated over the same RAG design space.
Deep neural networks (DNNs) deployed on resource-constrained neuromorphic hardware face three concurrent challenges: the need for model compression through pruning, vulnerability to adversarial input perturbations, and susceptibility to hardware-induced weight faults such as stuck-at-zero errors. While each of these factors has been studied in isolation, their combined effects on model reliability have received little attention. This paper presents an empirical investigation of how pruning, adversarial training, and hardware fault injection interact to affect the robustness of convolutional neural networks. Using a compact three-layer CNN trained on MNIST, we conduct three experiments: (1) comparing the fault tolerance of naturally and adversarially trained models under simultaneous hardware faults and adversarial attacks, (2) evaluating how pruning affects adversarial robustness, and (3) characterizing the joint accuracy surface across fault rates, adversarial perturbation magnitudes, and pruning levels. Our results show that adversarial training improves robustness against input perturbations but increases sensitivity to stuck-at-zero weight faults. Contrary to intuition, pruning did not significantly increase fault sensitivity, and varying the pruning level had little effect across fault rates and attack strengths. These results highlight the need to jointly consider adversarial robustness and hardware reliability.
展开完整摘要收起摘要↓
Deep neural networks (DNNs) deployed on resource-constrained neuromorphic hardware face three concurrent challenges: the need for model compression through pruning, vulnerability to adversarial input perturbations, and susceptibility to hardware-induced weight faults such as stuck-at-zero errors. While each of these factors has been studied in isolation, their combined effects on model reliability have received little attention. This paper presents an empirical investigation of how pruning, adversarial training, and hardware fault injection interact to affect the robustness of convolutional neural networks. Using a compact three-layer CNN trained on MNIST, we conduct three experiments: (1) comparing the fault tolerance of naturally and adversarially trained models under simultaneous hardware faults and adversarial attacks, (2) evaluating how pruning affects adversarial robustness, and (3) characterizing the joint accuracy surface across fault rates, adversarial perturbation magnitudes, and pruning levels. Our results show that adversarial training improves robustness against input perturbations but increases sensitivity to stuck-at-zero weight faults. Contrary to intuition, pruning did not significantly increase fault sensitivity, and varying the pruning level had little effect across fault rates and attack strengths. These results highlight the need to jointly consider adversarial robustness and hardware reliability.
作者Corey Lammie, Hadjer Benmeziane, William Andrew Simon, Irem Boybat
Heterogeneous DRAM-based processing-in-memory (PIM)-GPU systems promise significant efficiency gains for decode-phase large language model (LLM) inference, particularly in long-output generation, yet current design practices overlook critical factors that determine real-world performance. Through systematic evaluation of diverse architectures and workloads (OPT-7B/70B, Mamba2-2.7B/70B), we reveal three fundamental design principles: (i) static power consumption (DRAM leakage, refresh, and GPU idle power) can dominate the efficiency calculus, causing dynamic-only models to overestimate tokens/s/W by up to 3.85X for realistic deployments (Mamba2-2.7B, batch size 1, 128 input tokens, and 2,048 output tokens); (ii) decoding performance is monotonically non-decreasing with channel count across all evaluated models and workloads, generally plateauing at high channel counts for low-batch workloads; under a fixed-capacity sweep, all models instead share a common near-optimal hierarchy configuration, with substantially larger misconfiguration penalties for attention-based models; (iii) workload mapping strategies provide bounded improvements (up to 14.0%/17.4% kernel-level latency/energy reduction, up to 5.6% end-to-end gain) and are not primary bottlenecks. Significant efficiency gains require system-wide co-optimization. These principles provide design-space guidance for architects designing the next generation of memory-accelerated LLM systems.
展开完整摘要收起摘要↓
Heterogeneous DRAM-based processing-in-memory (PIM)-GPU systems promise significant efficiency gains for decode-phase large language model (LLM) inference, particularly in long-output generation, yet current design practices overlook critical factors that determine real-world performance. Through systematic evaluation of diverse architectures and workloads (OPT-7B/70B, Mamba2-2.7B/70B), we reveal three fundamental design principles: (i) static power consumption (DRAM leakage, refresh, and GPU idle power) can dominate the efficiency calculus, causing dynamic-only models to overestimate tokens/s/W by up to 3.85X for realistic deployments (Mamba2-2.7B, batch size 1, 128 input tokens, and 2,048 output tokens); (ii) decoding performance is monotonically non-decreasing with channel count across all evaluated models and workloads, generally plateauing at high channel counts for low-batch workloads; under a fixed-capacity sweep, all models instead share a common near-optimal hierarchy configuration, with substantially larger misconfiguration penalties for attention-based models; (iii) workload mapping strategies provide bounded improvements (up to 14.0%/17.4% kernel-level latency/energy reduction, up to 5.6% end-to-end gain) and are not primary bottlenecks. Significant efficiency gains require system-wide co-optimization. These principles provide design-space guidance for architects designing the next generation of memory-accelerated LLM systems.
Serving large language models (LLMs) under diverse deployment constraints requires flexible trade-offs between accuracy, memory footprint, and throughput. However, conventional quantization methods typically require a separate checkpoint for each target bit-width. We introduce Recurrent Residual Quantization (RRQ), a post-training quantization (PTQ) framework that represents weights as a low-bit quantized base together with a sequence of quantized residual corrections, enabling multiple effective precisions from a single checkpoint. Starting from a 2-bit model obtained via post-training quantization (PTQ) or round-to-nearest (RTN), RRQ progressively adds lightweight 2-bit residuals generated via RTN to construct 4-, 6-, and 8-bit representations. The method is calibration-free and avoids joint multi-bit optimization. In our Qwen3-8B setup, the full all-RTN 2-/4-/6-/8-bit package is constructed in 1,293 seconds, 3.3 times faster than the measured MatGPTQ construction. Experiments on six recent LLMs show competitive accuracy at 6 and 8 bits, with model-dependent behavior at 4 bits. The code will be made publicly available upon publication.
展开完整摘要收起摘要↓
Serving large language models (LLMs) under diverse deployment constraints requires flexible trade-offs between accuracy, memory footprint, and throughput. However, conventional quantization methods typically require a separate checkpoint for each target bit-width. We introduce Recurrent Residual Quantization (RRQ), a post-training quantization (PTQ) framework that represents weights as a low-bit quantized base together with a sequence of quantized residual corrections, enabling multiple effective precisions from a single checkpoint. Starting from a 2-bit model obtained via post-training quantization (PTQ) or round-to-nearest (RTN), RRQ progressively adds lightweight 2-bit residuals generated via RTN to construct 4-, 6-, and 8-bit representations. The method is calibration-free and avoids joint multi-bit optimization. In our Qwen3-8B setup, the full all-RTN 2-/4-/6-/8-bit package is constructed in 1,293 seconds, 3.3 times faster than the measured MatGPTQ construction. Experiments on six recent LLMs show competitive accuracy at 6 and 8 bits, with model-dependent behavior at 4 bits. The code will be made publicly available upon publication.
作者Samuel Fernández-Menduiña, Amir Ziashahabi, Eduardo Pavez, Antonio Ortega, Salman Avestimehr
Long-context LLM decoding reads the key-value (KV) cache at every step. Loading it takes longer than computing attention over it, so throughput is bandwidth-bound. Hence, reducing the cache size can raise both decoding speed and serving capacity. The challenge is to reduce cache size while preserving the attention products, keeping reconstruction cheap, and using a fixed per-token bit count. At two bits per element, the most competitive methods rely on orthogonal transforms. However, existing techniques are either data-oblivious or use the query statistics without deriving the transform from a distortion criterion. Moreover, they rely on transforms built on top of random or Hadamard rotations, which equalize variances across entries rather than compacting energy, and fixed-width scalar quantizers, which are suboptimal at low rates. In this paper, we formulate KV cache quantization as a transform coding problem in which distortion is the error in the attention products. We derive closed-form optimal transforms for keys and values from calibration statistics, under a high-resolution model. We show that the optimal key transform is not orthogonal and satisfies a generalized Parseval relation: the attention-aware distortion becomes mean-squared error (MSE) in the transform domain. Thus, we can use MSE-optimal vector quantizers applied directly to the transformed key coefficients. To meet the fixed-width layout requirement, we show that grouping coefficients into equal-volume partitions makes equal-size codebooks attain the variable-rate optimum under the same high-resolution model. At two bits per element, our method, termed NOVA-KV, recovers most of the long-context retrieval accuracy lost by scalar quantization methods at comparable throughput.
展开完整摘要收起摘要↓
Long-context LLM decoding reads the key-value (KV) cache at every step. Loading it takes longer than computing attention over it, so throughput is bandwidth-bound. Hence, reducing the cache size can raise both decoding speed and serving capacity. The challenge is to reduce cache size while preserving the attention products, keeping reconstruction cheap, and using a fixed per-token bit count. At two bits per element, the most competitive methods rely on orthogonal transforms. However, existing techniques are either data-oblivious or use the query statistics without deriving the transform from a distortion criterion. Moreover, they rely on transforms built on top of random or Hadamard rotations, which equalize variances across entries rather than compacting energy, and fixed-width scalar quantizers, which are suboptimal at low rates. In this paper, we formulate KV cache quantization as a transform coding problem in which distortion is the error in the attention products. We derive closed-form optimal transforms for keys and values from calibration statistics, under a high-resolution model. We show that the optimal key transform is not orthogonal and satisfies a generalized Parseval relation: the attention-aware distortion becomes mean-squared error (MSE) in the transform domain. Thus, we can use MSE-optimal vector quantizers applied directly to the transformed key coefficients. To meet the fixed-width layout requirement, we show that grouping coefficients into equal-volume partitions makes equal-size codebooks attain the variable-rate optimum under the same high-resolution model. At two bits per element, our method, termed NOVA-KV, recovers most of the long-context retrieval accuracy lost by scalar quantization methods at comparable throughput.
Graph inference over relational data can expose sensitive edge information, and this risk becomes more severe in dynamic graphs, where repeated model updates cause privacy loss to accumulate. We formulate Edge-level Differentially Private Dynamic Graph Inference (EDG) and propose PriDyG, a private inference framework that combines GNN-based structural learning with LLM-based semantic reasoning. PriDyG introduces incremental private multi-hop aggregation, which buffers newly arrived edges and processes each edge exactly once. By parallel composition, the total privacy cost equals that of a single static release, independent of the number or schedule of model updates. Compared with geometrically decaying budget allocation, incremental aggregation avoids exponentially increasing noise while preserving exact one-hop signals and at least half of two-hop information transfers. PriDyG further complements privatized GNN outputs with LLM predictions derived solely from node text, incurring no additional edge-level privacy cost. Experiments on four benchmarks for node classification and link prediction show that PriDyG consistently outperforms geometrically decaying baselines under the same privacy budget and matches the utility of naive per-update retraining while reducing cumulative privacy cost by up to three orders of magnitude.
展开完整摘要收起摘要↓
Graph inference over relational data can expose sensitive edge information, and this risk becomes more severe in dynamic graphs, where repeated model updates cause privacy loss to accumulate. We formulate Edge-level Differentially Private Dynamic Graph Inference (EDG) and propose PriDyG, a private inference framework that combines GNN-based structural learning with LLM-based semantic reasoning. PriDyG introduces incremental private multi-hop aggregation, which buffers newly arrived edges and processes each edge exactly once. By parallel composition, the total privacy cost equals that of a single static release, independent of the number or schedule of model updates. Compared with geometrically decaying budget allocation, incremental aggregation avoids exponentially increasing noise while preserving exact one-hop signals and at least half of two-hop information transfers. PriDyG further complements privatized GNN outputs with LLM predictions derived solely from node text, incurring no additional edge-level privacy cost. Experiments on four benchmarks for node classification and link prediction show that PriDyG consistently outperforms geometrically decaying baselines under the same privacy budget and matches the utility of naive per-update retraining while reducing cumulative privacy cost by up to three orders of magnitude.
When a language model follows an in-context conditional rule such as "if P(x) then A else B," does it assemble a runtime circuit with one module that tests the predicate and another that routes the answer? We probe this with activation patching under a four-donor design whose two swapped-rule donors make the condition and the answer word disagree, so each layer reveals which of the two it carries. Across three open models from two families and six languages sharing one fixed item bank, a mid-stack residual band carries the predicate's truth value: patching it reroutes the answer with predicate-outcome flip near 1.0 and mapping flip near 0.0, meeting a strict pre-specified isolation criterion in 17 of 18 cells, and the same localization holds across five predicate families. The router shows the opposite profile. A learned subspace flips A and B near-perfectly within the trained pair yet transfers to a new pair at approximately 0 in every model, while in Gemma-3-4B (the only model probed cross-lingually) it transfers at approximately 0.98 to the same pair in other languages. Under every probe we ran, the router direction is token-bound and non-transferable (largely answer-readout in Gemma, pair-specific in Qwen) rather than an abstract routing module. Test is modular; under these probes, route is not.
展开完整摘要收起摘要↓
When a language model follows an in-context conditional rule such as "if P(x) then A else B," does it assemble a runtime circuit with one module that tests the predicate and another that routes the answer? We probe this with activation patching under a four-donor design whose two swapped-rule donors make the condition and the answer word disagree, so each layer reveals which of the two it carries. Across three open models from two families and six languages sharing one fixed item bank, a mid-stack residual band carries the predicate's truth value: patching it reroutes the answer with predicate-outcome flip near 1.0 and mapping flip near 0.0, meeting a strict pre-specified isolation criterion in 17 of 18 cells, and the same localization holds across five predicate families. The router shows the opposite profile. A learned subspace flips A and B near-perfectly within the trained pair yet transfers to a new pair at approximately 0 in every model, while in Gemma-3-4B (the only model probed cross-lingually) it transfers at approximately 0.98 to the same pair in other languages. Under every probe we ran, the router direction is token-bound and non-transferable (largely answer-readout in Gemma, pair-specific in Qwen) rather than an abstract routing module. Test is modular; under these probes, route is not.
Just like software and hardware, business processes are susceptible to vulnerabilities that can lead to product quality issues, delays, and increased costs. Business process vulnerabilities can arise from a variety of sources, including conflicting requirements, ambiguous documentation, invalid measurement spec-ifications, omission of quality checks, or implementations that differ from speci-fications. MIRABELLE is a system that identifies and characterizes business logic (BL) vulnerabilities from available business process representations, in-cluding ISO 9000/9001 documentation, user guides, work instructions, and pro-cess execution logs. MIRABELLE leverages recent advances in AI/ML to pro-cess available business process documentation and generate attributed graph rep-resentations of the business logic that can be processed using both graph and for-mal logic approaches for identifying potential vulnerabilities. However, extract-ing the business logic (e.g., operation execution sequences, decisions, input/out-put resources) from mostly natural language artifacts is challenging due to the required domain expertise, inherent process complexity, and the sometimes very large volumes of information. This paper focuses on our experimentation with Large Language Models (LLMs) and their role within MIRABELLE. We report on the performance of several LLMs across vital stages of vulnerability detection, from grammatical and technical error-flagging in short phrasings, to complete process structure recovery and extraction.
展开完整摘要收起摘要↓
Just like software and hardware, business processes are susceptible to vulnerabilities that can lead to product quality issues, delays, and increased costs. Business process vulnerabilities can arise from a variety of sources, including conflicting requirements, ambiguous documentation, invalid measurement spec-ifications, omission of quality checks, or implementations that differ from speci-fications. MIRABELLE is a system that identifies and characterizes business logic (BL) vulnerabilities from available business process representations, in-cluding ISO 9000/9001 documentation, user guides, work instructions, and pro-cess execution logs. MIRABELLE leverages recent advances in AI/ML to pro-cess available business process documentation and generate attributed graph rep-resentations of the business logic that can be processed using both graph and for-mal logic approaches for identifying potential vulnerabilities. However, extract-ing the business logic (e.g., operation execution sequences, decisions, input/out-put resources) from mostly natural language artifacts is challenging due to the required domain expertise, inherent process complexity, and the sometimes very large volumes of information. This paper focuses on our experimentation with Large Language Models (LLMs) and their role within MIRABELLE. We report on the performance of several LLMs across vital stages of vulnerability detection, from grammatical and technical error-flagging in short phrasings, to complete process structure recovery and extraction.
Metaphorical language remains a major challenge for multilingual natural language processing because successful interpretation and translation require reasoning beyond literal lexical meaning. Existing research has largely investigated metaphor detection, machine translation, and translation evaluation as separate tasks, while little work has explored how these components can be integrated into a unified computational framework. This PhD proposal aims to develop an end-to-end framework for multilingual metaphor processing consisting of three complementary research directions: (1) robust metaphor detection across languages, (2) metaphor-oriented translation evaluation for both human assessment and automatic quality estimation, and (3) joint modelling that connects metaphor detection with translation evaluation. The proposed research will combine linguistic theory with recent advances in large language models to develop new datasets, annotation methodologies, evaluation benchmarks, and automatic evaluation approaches for metaphor-aware machine translation. The expected outcome is a unified framework that improves both the development and evaluation of multilingual NLP systems when processing figurative language.
展开完整摘要收起摘要↓
Metaphorical language remains a major challenge for multilingual natural language processing because successful interpretation and translation require reasoning beyond literal lexical meaning. Existing research has largely investigated metaphor detection, machine translation, and translation evaluation as separate tasks, while little work has explored how these components can be integrated into a unified computational framework. This PhD proposal aims to develop an end-to-end framework for multilingual metaphor processing consisting of three complementary research directions: (1) robust metaphor detection across languages, (2) metaphor-oriented translation evaluation for both human assessment and automatic quality estimation, and (3) joint modelling that connects metaphor detection with translation evaluation. The proposed research will combine linguistic theory with recent advances in large language models to develop new datasets, annotation methodologies, evaluation benchmarks, and automatic evaluation approaches for metaphor-aware machine translation. The expected outcome is a unified framework that improves both the development and evaluation of multilingual NLP systems when processing figurative language.
Reinforcement learning for flow-matching text-to-speech is complicated by deterministic ODE sampling: trajectory-level policy-gradient methods typically convert the ODE into an SDE and track per-step likelihood ratios, introducing stochastic perturbations and substantial overhead. We propose GROW, a group-relative advantage-weighted on-policy RL method that acts directly on the standard flow-matching objective. For each prompt, GROW samples a group of on-policy utterances, separately standardizes intelligibility and speaker-similarity rewards within the group, and combines them to reweight flow-matching regression. A Wasserstein-2 velocity penalty anchors the updated model to a frozen pretrained reference. A group-mean reward baseline is introduced to convert reward weighting into advantage weighting. For strong pretrained TTS models with concentrated rewards, positive exponential weighting is dominated by reward-agnostic self-imitation, whereas a zero-mean signed advantage preserves effective within-group credit assignment. Instantiated on DiTAR and evaluated on LibriSpeech and Seed-TTS EN/ZH, GROW reduces average WER from 2.016 to 1.558 and raises speaker similarity from 0.676 to 0.715 while keeping UTMOS. With 10-NFE training rollouts and 32-NFE evaluation, GROW retains comparable performance while training 2.9x faster than 32-NFE DiTAR-GRPO. We will open-source complete GROW codes, faithful DiTAR reproduction, and all model checkpoints.
展开完整摘要收起摘要↓
Reinforcement learning for flow-matching text-to-speech is complicated by deterministic ODE sampling: trajectory-level policy-gradient methods typically convert the ODE into an SDE and track per-step likelihood ratios, introducing stochastic perturbations and substantial overhead. We propose GROW, a group-relative advantage-weighted on-policy RL method that acts directly on the standard flow-matching objective. For each prompt, GROW samples a group of on-policy utterances, separately standardizes intelligibility and speaker-similarity rewards within the group, and combines them to reweight flow-matching regression. A Wasserstein-2 velocity penalty anchors the updated model to a frozen pretrained reference. A group-mean reward baseline is introduced to convert reward weighting into advantage weighting. For strong pretrained TTS models with concentrated rewards, positive exponential weighting is dominated by reward-agnostic self-imitation, whereas a zero-mean signed advantage preserves effective within-group credit assignment. Instantiated on DiTAR and evaluated on LibriSpeech and Seed-TTS EN/ZH, GROW reduces average WER from 2.016 to 1.558 and raises speaker similarity from 0.676 to 0.715 while keeping UTMOS. With 10-NFE training rollouts and 32-NFE evaluation, GROW retains comparable performance while training 2.9x faster than 32-NFE DiTAR-GRPO. We will open-source complete GROW codes, faithful DiTAR reproduction, and all model checkpoints.