Social power plays a fundamental role in shaping human interaction, yet computational studies of power remain limited to narrow linguistic and cultural settings. Existing datasets further lack the demographic and relational depth needed for robust cross-cultural analysis. To address this gap, we introduce a theoretically grounded framework for studying social power in naturalistic multilingual dialogue through movie screenplays. The framework integrates a schema informed by social science theory, a native speaker annotation pipeline refined through pilot studies, and a custom interface for scalable cross-lingual analysis. Using this framework, we constructed an initial corpus containing 15,836 annotated instances from 100 scenes in French and Egyptian Arabic movies. Our analysis reveals strong agreement on observable demographic and contextual attributes, while socially interpretive aspects, such as power asymmetry and intention alignment, remain more contested, highlighting the complexity of social power across cultures. We evaluated 6 Large Language Models (LLMs) and Multimodal LLMs on cross-cultural social power reasoning, finding persistent gaps between human and model agreement in relational and theory-of-mind reasoning. Our work introduces the first extensible multilingual framework for studying social power in dialogues and provides an initial evaluation setting for studying cross-cultural social reasoning.
展开完整摘要收起摘要↓
Social power plays a fundamental role in shaping human interaction, yet computational studies of power remain limited to narrow linguistic and cultural settings. Existing datasets further lack the demographic and relational depth needed for robust cross-cultural analysis. To address this gap, we introduce a theoretically grounded framework for studying social power in naturalistic multilingual dialogue through movie screenplays. The framework integrates a schema informed by social science theory, a native speaker annotation pipeline refined through pilot studies, and a custom interface for scalable cross-lingual analysis. Using this framework, we constructed an initial corpus containing 15,836 annotated instances from 100 scenes in French and Egyptian Arabic movies. Our analysis reveals strong agreement on observable demographic and contextual attributes, while socially interpretive aspects, such as power asymmetry and intention alignment, remain more contested, highlighting the complexity of social power across cultures. We evaluated 6 Large Language Models (LLMs) and Multimodal LLMs on cross-cultural social power reasoning, finding persistent gaps between human and model agreement in relational and theory-of-mind reasoning. Our work introduces the first extensible multilingual framework for studying social power in dialogues and provides an initial evaluation setting for studying cross-cultural social reasoning.
Multimodal GUI agents have emerged as a promising paradigm for digital task automation, yet transitioning from benchmark-oriented models to dependable real-world applications remains challenging due to limited environment coverage, brittle task construction, and unreliable reward verification. In this work, we present UI-Venus-2, a general-purpose foundation GUI agent designed to operate across mobile, web, and desktop environments through a unified closed-loop reasoning-action framework. To bridge the gap toward practical deployment, we jointly scale three critical dimensions: (1) Environments, expanding coverage to more than 170 multilingual mobile apps and native desktop operating systems; (2) Tasks, employing a deep-research pipeline for function-grounded instruction generation; and (3) Verification, adopting trace-level and sample-level evaluators with visual keypoints and multi-model voting to ensure reliable RL signals for training. Furthermore, we integrate safety-aware mechanisms to ensure controlled execution of consequential actions. By offering a capable, efficient, and open-source foundation, UI-Venus-2 advances the field toward more generalizable, verifiable, and self-reflective agents for real-world applications.
展开完整摘要收起摘要↓
Multimodal GUI agents have emerged as a promising paradigm for digital task automation, yet transitioning from benchmark-oriented models to dependable real-world applications remains challenging due to limited environment coverage, brittle task construction, and unreliable reward verification. In this work, we present UI-Venus-2, a general-purpose foundation GUI agent designed to operate across mobile, web, and desktop environments through a unified closed-loop reasoning-action framework. To bridge the gap toward practical deployment, we jointly scale three critical dimensions: (1) Environments, expanding coverage to more than 170 multilingual mobile apps and native desktop operating systems; (2) Tasks, employing a deep-research pipeline for function-grounded instruction generation; and (3) Verification, adopting trace-level and sample-level evaluators with visual keypoints and multi-model voting to ensure reliable RL signals for training. Furthermore, we integrate safety-aware mechanisms to ensure controlled execution of consequential actions. By offering a capable, efficient, and open-source foundation, UI-Venus-2 advances the field toward more generalizable, verifiable, and self-reflective agents for real-world applications.
作者Zike Yuan, Han Zhang, Jianzhi Yan, Le Liu, Cai Ke, Huozhi Zhou, Jian Xie, Jiran Yin, Yukun Cao, Yue Yu, Hui Wang, Ming Liu, Bing Qin
Despite their potential in standardized graph tasks, Large Language Models (LLMs) remain brittle to real-world shifts in node identifiers and task formulation. While deterministic graph tools are invariant to such shifts, extracting topological structures from noisy text is highly fragile for LLMs, which often overfit to surface patterns. Moreover, mitigating these parsing failures via multi-agent systems incurs prohibitive latency. To address this, we propose GRAIN, a single-agent framework optimized via reinforcement learning. GRAIN models reasoning as a semantic parsing and tool-execution pipeline, guided by a Structure Invariance Reward. By validating extracted intermediate graphs against ground-truth topologies, this reward forces the LLM to learn robust text-to-structure mappings rather than memorizing linguistic artifacts. We also introduce GRIT, a benchmark evaluating sensitivity to such linguistic shifts. GRAIN outperforms multi-agent baselines by 16.45% in accuracy with approximately 24% lower latency. Furthermore, it demonstrates superior structural generalization, halving the out-of-distribution (OOD) gap of SFT models (from 15.77% to 7.80%) and maintaining robustness on large-scale graphs beyond the training distribution.
展开完整摘要收起摘要↓
Despite their potential in standardized graph tasks, Large Language Models (LLMs) remain brittle to real-world shifts in node identifiers and task formulation. While deterministic graph tools are invariant to such shifts, extracting topological structures from noisy text is highly fragile for LLMs, which often overfit to surface patterns. Moreover, mitigating these parsing failures via multi-agent systems incurs prohibitive latency. To address this, we propose GRAIN, a single-agent framework optimized via reinforcement learning. GRAIN models reasoning as a semantic parsing and tool-execution pipeline, guided by a Structure Invariance Reward. By validating extracted intermediate graphs against ground-truth topologies, this reward forces the LLM to learn robust text-to-structure mappings rather than memorizing linguistic artifacts. We also introduce GRIT, a benchmark evaluating sensitivity to such linguistic shifts. GRAIN outperforms multi-agent baselines by 16.45% in accuracy with approximately 24% lower latency. Furthermore, it demonstrates superior structural generalization, halving the out-of-distribution (OOD) gap of SFT models (from 15.77% to 7.80%) and maintaining robustness on large-scale graphs beyond the training distribution.
Scripted and rule-based non-player characters (NPCs) in combat video games often exhibit predictable behaviors that experienced players can exploit, while reinforcement learning (RL) agents typically retain a fixed policy after training and cannot readily adapt their strategy to different opponents. We investigate a runtime strategy-selection framework in which a large language model (LLM) guides a trained RL policy without modifying its underlying behavior. To demonstrate this, we train five NPC agents with a shared PPO policy in Unity and compare a baseline configuration, in which the policy acts independently, with an LLM-augmented configuration in which a locally hosted Mistral 7B model, accessed through Ollama, reads the live game state every five seconds and assigns one of four tactical tags. We evaluate both configurations against three scripted opponent types across 600 episodes and analyze outcomes using the Mann-Whitney U test. Against a Balanced opponent that changes tactics during an episode, the LLM-augmented agents more than doubled their win rate from 11% to 24% and produced significantly longer episodes. Against an Evasive opponent, the augmented agents achieved a higher win rate and faster kills, although their shorter episode duration did not satisfy the strict hypothesis definition. Against an Aggressive opponent, the LLM's near-constant preference for encirclement was counterproductive. Analysis of 2,430 strategy selections showed that Surround was selected in 83.8% of cases regardless of opponent type, indicating limited zero-shot strategic differentiation at this model scale. These results demonstrate both the potential and limitations of LLM-guided runtime strategy selection for adaptive multi-agent game AI.
展开完整摘要收起摘要↓
Scripted and rule-based non-player characters (NPCs) in combat video games often exhibit predictable behaviors that experienced players can exploit, while reinforcement learning (RL) agents typically retain a fixed policy after training and cannot readily adapt their strategy to different opponents. We investigate a runtime strategy-selection framework in which a large language model (LLM) guides a trained RL policy without modifying its underlying behavior. To demonstrate this, we train five NPC agents with a shared PPO policy in Unity and compare a baseline configuration, in which the policy acts independently, with an LLM-augmented configuration in which a locally hosted Mistral 7B model, accessed through Ollama, reads the live game state every five seconds and assigns one of four tactical tags. We evaluate both configurations against three scripted opponent types across 600 episodes and analyze outcomes using the Mann-Whitney U test. Against a Balanced opponent that changes tactics during an episode, the LLM-augmented agents more than doubled their win rate from 11% to 24% and produced significantly longer episodes. Against an Evasive opponent, the augmented agents achieved a higher win rate and faster kills, although their shorter episode duration did not satisfy the strict hypothesis definition. Against an Aggressive opponent, the LLM's near-constant preference for encirclement was counterproductive. Analysis of 2,430 strategy selections showed that Surround was selected in 83.8% of cases regardless of opponent type, indicating limited zero-shot strategic differentiation at this model scale. These results demonstrate both the potential and limitations of LLM-guided runtime strategy selection for adaptive multi-agent game AI.
作者Alistair Reid, Simon O'Callaghan, Dustin Venini, Liam Carroll, Tiberio Caetano
This report presents a framework to help organisations, policymakers and researchers reason about the risks that emerge when AI agents interact with each other, how those risks change as interactions cross organisational boundaries, and the controls that may help address them. As organisations deploy AI agents, those agents will increasingly interact with each other: inside the organisation, with the agents of partners, customers and suppliers, and with unknown counterparties on the open internet. Failures can emerge from the interactions themselves, and once those interactions cross an organisation's perimeter, no single organisation can fully see, control or govern them. The report introduces three deployment tiers, defined by the minimum common governance binding any two interacting agents: singular governance, where one organisation governs every agent; federated governance, where multiple organisations deploy into a shared environment under agreed rules; and open environments, where agents operate with no central authority and shared standards are adopted voluntarily if at all. Within each tier, the report examines risk factors, failure modes and available controls. It identifies who is positioned to apply the controls, and where no actor is positioned to act, it characterises the gap and the collective action required to close it.
展开完整摘要收起摘要↓
This report presents a framework to help organisations, policymakers and researchers reason about the risks that emerge when AI agents interact with each other, how those risks change as interactions cross organisational boundaries, and the controls that may help address them. As organisations deploy AI agents, those agents will increasingly interact with each other: inside the organisation, with the agents of partners, customers and suppliers, and with unknown counterparties on the open internet. Failures can emerge from the interactions themselves, and once those interactions cross an organisation's perimeter, no single organisation can fully see, control or govern them. The report introduces three deployment tiers, defined by the minimum common governance binding any two interacting agents: singular governance, where one organisation governs every agent; federated governance, where multiple organisations deploy into a shared environment under agreed rules; and open environments, where agents operate with no central authority and shared standards are adopted voluntarily if at all. Within each tier, the report examines risk factors, failure modes and available controls. It identifies who is positioned to apply the controls, and where no actor is positioned to act, it characterises the gap and the collective action required to close it.
作者Vaishnavi Nagabhushana, Kartikay Agrawal, Ayon Borthakur
Robotic and edge intelligence systems operate in dynamic environments where data arrives continuously, requiring models to adapt while preserving previously learned knowledge under strict memory and energy constraints. While parameter-efficient fine-tuning has shown promise for continual learning with vision transformers, conventional architectures rely on dense computation and remain costly for real-world deployment. Sparse event-based vision transformers provide energy-efficient event-driven computation, yet their continual learning capabilities remain largely unexplored. We here introduce sLoTh, a parameter-efficient continual learning framework for pretrained sparse event-based (spiking) vision transformers. sLoTh freezes the backbone and restricts plasticity to scalable-efficient low-rank attention updates (seLoRA) and shared neuronal threshold modulation, enabling adaptation without replay buffers by updating less than 1% of model parameters. Experiments across CIFAR-100, Tiny-ImageNet, ImageNet-100, and ImageNet-R with up to 100 tasks demonstrate competitive rehearsal-free performance in class-incremental learning and online continual learning, while enabling approximately 6.5x lower energy consumption than conventional dense vision transformers.
展开完整摘要收起摘要↓
Robotic and edge intelligence systems operate in dynamic environments where data arrives continuously, requiring models to adapt while preserving previously learned knowledge under strict memory and energy constraints. While parameter-efficient fine-tuning has shown promise for continual learning with vision transformers, conventional architectures rely on dense computation and remain costly for real-world deployment. Sparse event-based vision transformers provide energy-efficient event-driven computation, yet their continual learning capabilities remain largely unexplored. We here introduce sLoTh, a parameter-efficient continual learning framework for pretrained sparse event-based (spiking) vision transformers. sLoTh freezes the backbone and restricts plasticity to scalable-efficient low-rank attention updates (seLoRA) and shared neuronal threshold modulation, enabling adaptation without replay buffers by updating less than 1% of model parameters. Experiments across CIFAR-100, Tiny-ImageNet, ImageNet-100, and ImageNet-R with up to 100 tasks demonstrate competitive rehearsal-free performance in class-incremental learning and online continual learning, while enabling approximately 6.5x lower energy consumption than conventional dense vision transformers.
作者Tian Chen, Nawras Alnaasan, Jinghan Yao, Aamir Shafi, Hari Subramoni, Dhabaleswar K., Panda
Data preprocessing is a crucial part of deep learning workflows on edge devices. However, decoding data saved in JPEG format is very compute-intensive and occupies a major portion of the preprocessing pipeline. Therefore, increasing the decoding speed is vital for improving overall throughput, especially for inputs with large image sizes, which are often subject to preprocessing bottlenecks. On the other hand, edge devices are equipped with specialized hardware units to accelerate media processing and image decoding. For instance, the NVIDIA Jetson platform possesses a dedicated NVJPEG unit. These units can be used to enhance the performance of the preprocessing pipeline. This paper introduces the utilization of such specific hardware acceleration units for offloading decoding tasks. By combining this with a multi-instance approach, it allows for the parallelization of all compute resources including CPU, NVJPEG, GPU, and DLA in Jetson devices. In this work, we compare various potential pipeline designs. On ResNet18, ResNet50, and ResNet152, three models with different sizes, we evaluate the impact of batch sizes and image sizes, as well as the characteristics of GPU/DLA inference. Finally, a fine-tuning experiment for multi-instance design has been conducted. The multi-instance design with a specific hardware decoding unit involved offers up to 30.02% speedup for large image sizes, compared with the most optimized design without it. Based on these findings, we demonstrate the benefits of using the NVJPEG unit in deep learning workflows and provide guidelines for tuning and optimizing edge inference workflows.
展开完整摘要收起摘要↓
Data preprocessing is a crucial part of deep learning workflows on edge devices. However, decoding data saved in JPEG format is very compute-intensive and occupies a major portion of the preprocessing pipeline. Therefore, increasing the decoding speed is vital for improving overall throughput, especially for inputs with large image sizes, which are often subject to preprocessing bottlenecks. On the other hand, edge devices are equipped with specialized hardware units to accelerate media processing and image decoding. For instance, the NVIDIA Jetson platform possesses a dedicated NVJPEG unit. These units can be used to enhance the performance of the preprocessing pipeline. This paper introduces the utilization of such specific hardware acceleration units for offloading decoding tasks. By combining this with a multi-instance approach, it allows for the parallelization of all compute resources including CPU, NVJPEG, GPU, and DLA in Jetson devices. In this work, we compare various potential pipeline designs. On ResNet18, ResNet50, and ResNet152, three models with different sizes, we evaluate the impact of batch sizes and image sizes, as well as the characteristics of GPU/DLA inference. Finally, a fine-tuning experiment for multi-instance design has been conducted. The multi-instance design with a specific hardware decoding unit involved offers up to 30.02% speedup for large image sizes, compared with the most optimized design without it. Based on these findings, we demonstrate the benefits of using the NVJPEG unit in deep learning workflows and provide guidelines for tuning and optimizing edge inference workflows.
作者Jacopo Dardini, Claudio Stanzione, Giordano Colò, Giuseppe Fenza
Post-training quantization is often treated as a semantically neutral optimization for edge deployment of Large Language Models. When a full-precision source checkpoint is evaluated and quantization is applied downstream without equivalent re-evaluation, this workflow creates a structural validation--deployment gap: because quantization is a many-to-one mapping over parameter space, source-precision certification does not guarantee behavioral equivalence in the deployed configuration. We formalize this gap through Quantization Behavioral Equivalence Classes (QBECs) and prove that QBEC membership does not imply behavioral equivalence, providing a theoretical basis for quantization-triggered backdoor attacks. Building on a three-stage adversarial fine-tuning framework, we embed latent malicious payloads into models that satisfy the source-precision checks used in our evaluation, yet activate targeted adversarial behavior upon INT8 or 4-bit compression. We evaluate this threat in two operationally motivated scenarios, tactical machine translation and political content analysis, extending prior work from decoder-only causal LMs to multilingual encoder-decoder sequence-to-sequence models. Results show that backdoored translation models move from zero measured friend--foe corruption at repaired FP16 to up to 85.02% inversion after quantization, and that a paired stance classifier measures an ideological shift of up to $Δ\mathrm{Bias}=0.33$ upon compression. A cross-quantizer transferability analysis further shows that attack persistence varies across quantization schemes and model architectures, rather than being determined by nominal bit-width alone. These findings demonstrate that source-precision auditing alone does not rule out quantization-triggered behavior and that the final deployed configuration must be included in behavioral certification for trustworthy edge AI.
展开完整摘要收起摘要↓
Post-training quantization is often treated as a semantically neutral optimization for edge deployment of Large Language Models. When a full-precision source checkpoint is evaluated and quantization is applied downstream without equivalent re-evaluation, this workflow creates a structural validation--deployment gap: because quantization is a many-to-one mapping over parameter space, source-precision certification does not guarantee behavioral equivalence in the deployed configuration. We formalize this gap through Quantization Behavioral Equivalence Classes (QBECs) and prove that QBEC membership does not imply behavioral equivalence, providing a theoretical basis for quantization-triggered backdoor attacks. Building on a three-stage adversarial fine-tuning framework, we embed latent malicious payloads into models that satisfy the source-precision checks used in our evaluation, yet activate targeted adversarial behavior upon INT8 or 4-bit compression. We evaluate this threat in two operationally motivated scenarios, tactical machine translation and political content analysis, extending prior work from decoder-only causal LMs to multilingual encoder-decoder sequence-to-sequence models. Results show that backdoored translation models move from zero measured friend--foe corruption at repaired FP16 to up to 85.02% inversion after quantization, and that a paired stance classifier measures an ideological shift of up to $Δ\mathrm{Bias}=0.33$ upon compression. A cross-quantizer transferability analysis further shows that attack persistence varies across quantization schemes and model architectures, rather than being determined by nominal bit-width alone. These findings demonstrate that source-precision auditing alone does not rule out quantization-triggered behavior and that the final deployed configuration must be included in behavioral certification for trustworthy edge AI.
作者Zifan Wang, Ziang Ren, Pengyang Shi, Zirui Wang, Chenghuai Lin, Tianze Wang, Zekun Qi, Liangliang Zhao, He Wang, Li Yi
Enabling humanoid robots to respond to human speech with synchronized and semantically meaningful gestures is fundamental to natural human-robot interaction. However, this task faces three critical barriers: the scarcity of semantically rich datasets, the "modality eclipse" where models ignore audio cues in favor of kinematic inertia, and the sim-to-real gap regarding physical safety. We propose RoboGesture, a robot-centric framework that co-designs data, modeling, and control to power a complete interactive human-humanoid system in which the robot listens, responds, and gestures in real time. We first establish the RoboGesture dataset featuring over 300 gesture categories and develop an automated pipeline to synthesize large-scale collision-free, robot-specific audio-motion pairs. Our architecture features a Hierarchical Semantic-Acoustic Aligner that extracts multi-granular prosodic and semantic cues directly from raw audio tokens. These cues drive a Streaming Conditional Motion Generator based on a diffusion transformer with conditional flow matching. To ensure high responsiveness, we introduce Anti-Inertia CFG Masking, which prevents the model from collapsing into repetitive historical patterns by compelling it to proactively mine control signals from the audio modality. Finally, an MPC-based safety filter ensures real-time, collision-free execution on physical hardware. Experiments on a Unitree G1 humanoid demonstrate that RoboGesture generates safer, more rhythmic, and more semantically appropriate responses compared to state-of-the-art baselines.
展开完整摘要收起摘要↓
Enabling humanoid robots to respond to human speech with synchronized and semantically meaningful gestures is fundamental to natural human-robot interaction. However, this task faces three critical barriers: the scarcity of semantically rich datasets, the "modality eclipse" where models ignore audio cues in favor of kinematic inertia, and the sim-to-real gap regarding physical safety. We propose RoboGesture, a robot-centric framework that co-designs data, modeling, and control to power a complete interactive human-humanoid system in which the robot listens, responds, and gestures in real time. We first establish the RoboGesture dataset featuring over 300 gesture categories and develop an automated pipeline to synthesize large-scale collision-free, robot-specific audio-motion pairs. Our architecture features a Hierarchical Semantic-Acoustic Aligner that extracts multi-granular prosodic and semantic cues directly from raw audio tokens. These cues drive a Streaming Conditional Motion Generator based on a diffusion transformer with conditional flow matching. To ensure high responsiveness, we introduce Anti-Inertia CFG Masking, which prevents the model from collapsing into repetitive historical patterns by compelling it to proactively mine control signals from the audio modality. Finally, an MPC-based safety filter ensures real-time, collision-free execution on physical hardware. Experiments on a Unitree G1 humanoid demonstrate that RoboGesture generates safer, more rhythmic, and more semantically appropriate responses compared to state-of-the-art baselines.
作者Matiur Rahman Minar, Seunghun Oh, Ganghyeon Jeong, Unsang Park
Long-horizon video generation is evaluated with whole-frame metrics that reward motion and temporal consistency. For fixed-camera nature scenes this creates an ambiguity: motion of water, fire, smoke, or rain is desirable, whereas motion of the background is an error. A system can therefore score well on motion while its scene drifts, or on consistency while its flow stagnates. We introduce SNF-Bench, an evaluation framework for long-horizon fixed-camera generation that partitions each scene into static support and dynamic flow and reports static fidelity, flow persistence with absolute magnitude, and drift leakage separately, never as one score. Drift leakage is interpretive context rather than a headline measurement. Each factor is validated mechanistically rather than by correlation with preference: we inject global translation, rotation, and scale drift and progressive late freezing at known severity into real generations, and require each factor to respond in its stated direction and to remain selective against corruptions it does not target. Auditing publicly released long-horizon text-conditioned checkpoints under one recorded common inference configuration, plus an image-conditioned track with released-pipeline references and a deployment-sensitivity panel, we find that whole-frame motion and static-region drift induce near-opposite orderings of the same outputs. At maximum controlled translation, fBD and NBF rise to $1.86\times$ and $1.32\times$ baseline, but whole-frame Dynamic Degree reaches only $1.07\times$---rewarding the corruption. SNF-Bench measures where motion occurs and whether it persists; it does not measure physical realism. Project page: https://minar09.github.io/snfbench/.
展开完整摘要收起摘要↓
Long-horizon video generation is evaluated with whole-frame metrics that reward motion and temporal consistency. For fixed-camera nature scenes this creates an ambiguity: motion of water, fire, smoke, or rain is desirable, whereas motion of the background is an error. A system can therefore score well on motion while its scene drifts, or on consistency while its flow stagnates. We introduce SNF-Bench, an evaluation framework for long-horizon fixed-camera generation that partitions each scene into static support and dynamic flow and reports static fidelity, flow persistence with absolute magnitude, and drift leakage separately, never as one score. Drift leakage is interpretive context rather than a headline measurement. Each factor is validated mechanistically rather than by correlation with preference: we inject global translation, rotation, and scale drift and progressive late freezing at known severity into real generations, and require each factor to respond in its stated direction and to remain selective against corruptions it does not target. Auditing publicly released long-horizon text-conditioned checkpoints under one recorded common inference configuration, plus an image-conditioned track with released-pipeline references and a deployment-sensitivity panel, we find that whole-frame motion and static-region drift induce near-opposite orderings of the same outputs. At maximum controlled translation, fBD and NBF rise to $1.86\times$ and $1.32\times$ baseline, but whole-frame Dynamic Degree reaches only $1.07\times$---rewarding the corruption. SNF-Bench measures where motion occurs and whether it persists; it does not measure physical realism. Project page: https://minar09.github.io/snfbench/.
Deformable 3D Gaussian Splatting (D-3DGS) reconstructs dynamic scenes by deforming a canonical set of 3D Gaussians through a deformation field of frame time. Replacing its MLP with a stack of Closed-form Continuous-time (CfC) cells-a Liquid Neural Network that solves the Liquid Timeconstant ODE in closed form-gives the field continuous-time behaviour at feed-forward cost. That closed form, however, is only the deterministic limit of a noise-driven system, and drops the stochastic term usually credited for the robustness of liquid networks. We put it back: a small Gaussian perturbation is added to the time gate of every CfC cell, turning the deterministic field into a simple stochastic (SDE) one. The noise is used only during training, needs no solver, and reduces exactly to the CfC when switched off. On the synthetic D-NeRF scenes the stochastic field is on par with the deterministic CfC and beats the MLP baseline on most scenes; on the real-world NeRF-DS scenes the deterministic limit is already best and adding noise does not help. The study thus gives both a clean way to read the CfC field as an SDE and an honest account of when a plain noise term helps and when it does not.
展开完整摘要收起摘要↓
Deformable 3D Gaussian Splatting (D-3DGS) reconstructs dynamic scenes by deforming a canonical set of 3D Gaussians through a deformation field of frame time. Replacing its MLP with a stack of Closed-form Continuous-time (CfC) cells-a Liquid Neural Network that solves the Liquid Timeconstant ODE in closed form-gives the field continuous-time behaviour at feed-forward cost. That closed form, however, is only the deterministic limit of a noise-driven system, and drops the stochastic term usually credited for the robustness of liquid networks. We put it back: a small Gaussian perturbation is added to the time gate of every CfC cell, turning the deterministic field into a simple stochastic (SDE) one. The noise is used only during training, needs no solver, and reduces exactly to the CfC when switched off. On the synthetic D-NeRF scenes the stochastic field is on par with the deterministic CfC and beats the MLP baseline on most scenes; on the real-world NeRF-DS scenes the deterministic limit is already best and adding noise does not help. The study thus gives both a clean way to read the CfC field as an SDE and an honest account of when a plain noise term helps and when it does not.
Additive manufacturing (AM) enables compact hydraulic components whose internal fluid channels can follow free-form 3D paths rather than conventionally drilled holes. A representative case is multi-group channel layout in rotary direct-drive servo valves: once a channel is placed it permanently occupies volume, so later channels must clear earlier geometry--unlike classical multi-agent pathfinding (MAPF), where agents free space after moving. We study this setting as multi-group pipe routing under permanent geometric occupancy. Our contributions are a problem formalization with geometric dual-witness conflicts, a constructive 3D benchmark (two corridor generators x two obstacle painters, controlled difficulty, feasibility witnesses), and baseline results for CBS, PBS, and priority planning adapted to this coupling. We evaluate by success rate under a fixed time budget. PlaneSlice hard instances clearly rank CBS above PBS and PP, while easier cells validate the pipeline. The goal is a reproducible problem definition, suite, and classical baselines--not a new optimal MAPF algorithm.
展开完整摘要收起摘要↓
Additive manufacturing (AM) enables compact hydraulic components whose internal fluid channels can follow free-form 3D paths rather than conventionally drilled holes. A representative case is multi-group channel layout in rotary direct-drive servo valves: once a channel is placed it permanently occupies volume, so later channels must clear earlier geometry--unlike classical multi-agent pathfinding (MAPF), where agents free space after moving. We study this setting as multi-group pipe routing under permanent geometric occupancy. Our contributions are a problem formalization with geometric dual-witness conflicts, a constructive 3D benchmark (two corridor generators x two obstacle painters, controlled difficulty, feasibility witnesses), and baseline results for CBS, PBS, and priority planning adapted to this coupling. We evaluate by success rate under a fixed time budget. PlaneSlice hard instances clearly rank CBS above PBS and PP, while easier cells validate the pipeline. The goal is a reproducible problem definition, suite, and classical baselines--not a new optimal MAPF algorithm.
作者Deblina Kar, Anant Nawalgaria, Shyamal Kumar Das Mandal
AI agents increasingly perform long-term reasoning, planning, tool use, memory integration, and autonomous decision making, yet erroneous intermediate states can propagate and cause inconsistent decisions and unreliable outputs. Existing reasoning approaches mainly rely on iterative planning, self-reflection, augmented memory, or verification, but rarely localize and selectively repair faulty reasoning. We present ORDDAR (Observation-Driven Reasoning for Distortion-Resilient Decision, Action, and Cognitive Recovery), a reasoning framework that models reasoning as cognitive state transitions, detects localized distortions, retrieves related reasoning from prior experiences, and repairs only the affected states. ORDDAR therefore performs recovery at the local reasoning-transition level rather than regenerating the complete trajectory. Experiments across mathematical, commonsense, multi-hop, and clinical reasoning benchmarks demonstrate improved reasoning quality, recovery ability, and interpretability over multiple evaluated reasoning baselines.
展开完整摘要收起摘要↓
AI agents increasingly perform long-term reasoning, planning, tool use, memory integration, and autonomous decision making, yet erroneous intermediate states can propagate and cause inconsistent decisions and unreliable outputs. Existing reasoning approaches mainly rely on iterative planning, self-reflection, augmented memory, or verification, but rarely localize and selectively repair faulty reasoning. We present ORDDAR (Observation-Driven Reasoning for Distortion-Resilient Decision, Action, and Cognitive Recovery), a reasoning framework that models reasoning as cognitive state transitions, detects localized distortions, retrieves related reasoning from prior experiences, and repairs only the affected states. ORDDAR therefore performs recovery at the local reasoning-transition level rather than regenerating the complete trajectory. Experiments across mathematical, commonsense, multi-hop, and clinical reasoning benchmarks demonstrate improved reasoning quality, recovery ability, and interpretability over multiple evaluated reasoning baselines.
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Visual Question Answering (VQA), yet they continue to struggle with questions requiring precise spatial reasoning and fine-grained visual understanding. These limitations often manifest as object, attribute, and spatial hallucinations, where models generate confident but visually unsupported responses due to insufficient region-level and fine-grained visual grounding. To address this challenge, we propose ReVA, a region-aware VQA model that employs a frozen CLIP ViT-L/14 Vision Transformer (ViT) and a Qwen2.5-7B-Instruct large language model (LLM) connected through a dual bridge that aligns both whole-image and region-level representations with the LLM's embedding space. The image bridge maps final transformer block features into image tokens. The region bridge maps cropped features from enriched intermediate features across ViT blocks so early texture and later object cues are more evident, into K region tokens for every bounding box. ReVA uses a detector stack that supplies automatic zero-shot bounding boxes that are both question-agnostic and question-dependent, using RAM++ (Recognize Anything Model), spaCy, and Grounding DINO. The image tokens and region tokens are concatenated as an LLM prompt prefix to jointly encode scene-level context and fine-grained regional evidence when answering questions. Evaluated on VQAv2, MMBench, POPE, and SEED-Bench, ReVA achieves 82.85% mean F1 on POPE, compared with 81.14% for an image-token baseline without region tokens. These results demonstrate that explicit region-aware visual representations reduce object hallucination and improve the factual grounding of MLLMs.
展开完整摘要收起摘要↓
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Visual Question Answering (VQA), yet they continue to struggle with questions requiring precise spatial reasoning and fine-grained visual understanding. These limitations often manifest as object, attribute, and spatial hallucinations, where models generate confident but visually unsupported responses due to insufficient region-level and fine-grained visual grounding. To address this challenge, we propose ReVA, a region-aware VQA model that employs a frozen CLIP ViT-L/14 Vision Transformer (ViT) and a Qwen2.5-7B-Instruct large language model (LLM) connected through a dual bridge that aligns both whole-image and region-level representations with the LLM's embedding space. The image bridge maps final transformer block features into image tokens. The region bridge maps cropped features from enriched intermediate features across ViT blocks so early texture and later object cues are more evident, into K region tokens for every bounding box. ReVA uses a detector stack that supplies automatic zero-shot bounding boxes that are both question-agnostic and question-dependent, using RAM++ (Recognize Anything Model), spaCy, and Grounding DINO. The image tokens and region tokens are concatenated as an LLM prompt prefix to jointly encode scene-level context and fine-grained regional evidence when answering questions. Evaluated on VQAv2, MMBench, POPE, and SEED-Bench, ReVA achieves 82.85% mean F1 on POPE, compared with 81.14% for an image-token baseline without region tokens. These results demonstrate that explicit region-aware visual representations reduce object hallucination and improve the factual grounding of MLLMs.
Function routing — selecting the correct API call from a fixed catalog given a natural-language request — is a deployment problem where small students are attractive but knowledge distillation gains are typically reported single-seed, at scales where seed variance is unknown. On a 740-instance healthcare API routing task with a 1.5B Qwen student and a 20B teacher, we compare eight KD variants against supervised cross-entropy, using three to six seeds for key configurations. We find: (i) per-seed standard deviation ranges from 2.8 to 48.7 percentage points, swallowing every claimed KD gain below five points; (ii) three of seven KD variants exhibit bimodal collapse, with at least one in three to five seeds falling below 55% accuracy while the others train normally, and a fourth showing elevated variance; (iii) collapse has distinct modes — wrong-function selection for ce_kd and ce_paraphrase, and a previously undocumented output-truncation mode for reasoning_kd, where the model emits reasoning but terminates before producing a function name (0.9% accuracy); (iv) only progressive_kd and rank_kd avoid collapse across observed seeds, with sigma <= 3.9 pp; (v) a naive cross-split +3.78 pp gain from input enrichment reverses to -2.70 pp under controlled within-split multi-seed re-testing. Single-seed evaluation is therefore unable to detect central failure modes in small-model KD.
展开完整摘要收起摘要↓
Function routing — selecting the correct API call from a fixed catalog given a natural-language request — is a deployment problem where small students are attractive but knowledge distillation gains are typically reported single-seed, at scales where seed variance is unknown. On a 740-instance healthcare API routing task with a 1.5B Qwen student and a 20B teacher, we compare eight KD variants against supervised cross-entropy, using three to six seeds for key configurations. We find: (i) per-seed standard deviation ranges from 2.8 to 48.7 percentage points, swallowing every claimed KD gain below five points; (ii) three of seven KD variants exhibit bimodal collapse, with at least one in three to five seeds falling below 55% accuracy while the others train normally, and a fourth showing elevated variance; (iii) collapse has distinct modes — wrong-function selection for ce_kd and ce_paraphrase, and a previously undocumented output-truncation mode for reasoning_kd, where the model emits reasoning but terminates before producing a function name (0.9% accuracy); (iv) only progressive_kd and rank_kd avoid collapse across observed seeds, with sigma <= 3.9 pp; (v) a naive cross-split +3.78 pp gain from input enrichment reverses to -2.70 pp under controlled within-split multi-seed re-testing. Single-seed evaluation is therefore unable to detect central failure modes in small-model KD.
GUI agents trained with reinforcement learning (RL) have showcased strong environment learning capabilities on mobile platforms. However, RL typically demands extensive real-environment interactions, leading to high resource costs and instability, especially in GUI scenarios. To address these, we propose WM-R1, the first reinforcement learning framework that trains mobile GUI agents with world models instead of real environments. Specifically, world models serve as the source of state transitions during all rollouts, replacing the real Android environment within the training loop. WM-R1 also embeds world models directly into the thinking process, enabling agents to reason about the consequences of candidate actions before committing to the final action. Crucially, WM-R1 eliminates the need for real-environment interaction, supports massively parallelized and step-level granularized trajectory generation grounded in world models, and introduces a multi-dimensional rule-based reward that jointly optimizes task success, trajectory efficiency, and world model utilization. For efficient training, we curate a high-quality dataset of 2000 challenging tasks. Experiments on Android mobile benchmarks demonstrate that WM-R1-trained agents significantly outperform GRPO-only baselines and inference-time simulation methods. Code is available at https://github.com/genalyu/WM-R1 .
展开完整摘要收起摘要↓
GUI agents trained with reinforcement learning (RL) have showcased strong environment learning capabilities on mobile platforms. However, RL typically demands extensive real-environment interactions, leading to high resource costs and instability, especially in GUI scenarios. To address these, we propose WM-R1, the first reinforcement learning framework that trains mobile GUI agents with world models instead of real environments. Specifically, world models serve as the source of state transitions during all rollouts, replacing the real Android environment within the training loop. WM-R1 also embeds world models directly into the thinking process, enabling agents to reason about the consequences of candidate actions before committing to the final action. Crucially, WM-R1 eliminates the need for real-environment interaction, supports massively parallelized and step-level granularized trajectory generation grounded in world models, and introduces a multi-dimensional rule-based reward that jointly optimizes task success, trajectory efficiency, and world model utilization. For efficient training, we curate a high-quality dataset of 2000 challenging tasks. Experiments on Android mobile benchmarks demonstrate that WM-R1-trained agents significantly outperform GRPO-only baselines and inference-time simulation methods. Code is available at https://github.com/genalyu/WM-R1 .
A model's behavior on a task is jointly determined by the input it receives and the prior it brings in, i.e. the distribution over stimuli it implicitly expects. Interpretability research has traditionally studied models by holding inputs fixed and examining model responses either mechanistically, probing how internal structure represents inputs, or behaviorally, measuring how variation in inputs leads to variation in outputs. Neither reconstructs the prior distribution itself, since internal structure shows what a model can represent, not what it expects, and any fixed stimulus set leaves most of the possible input space unseen. In particular, such an input space in real-world settings, such as images seen by VLMs, is extremely high-dimensional and diverse. These priors thus remain a poorly understood component of models that nonetheless influence real-world behavior. We propose a method to sample from models' perceptual prior distributions directly, by steering a generative model to produce stimuli along controllable axes and running Gibbs sampling over that space with the model under study as the judge. We apply this to a variety of categories and target variables (such as trustworthiness in faces and cheapness in art images) and recover both canonical biases and surprising novel priors invisible to direct prompting, warranting further investigation of their downstream effects.
展开完整摘要收起摘要↓
A model's behavior on a task is jointly determined by the input it receives and the prior it brings in, i.e. the distribution over stimuli it implicitly expects. Interpretability research has traditionally studied models by holding inputs fixed and examining model responses either mechanistically, probing how internal structure represents inputs, or behaviorally, measuring how variation in inputs leads to variation in outputs. Neither reconstructs the prior distribution itself, since internal structure shows what a model can represent, not what it expects, and any fixed stimulus set leaves most of the possible input space unseen. In particular, such an input space in real-world settings, such as images seen by VLMs, is extremely high-dimensional and diverse. These priors thus remain a poorly understood component of models that nonetheless influence real-world behavior. We propose a method to sample from models' perceptual prior distributions directly, by steering a generative model to produce stimuli along controllable axes and running Gibbs sampling over that space with the model under study as the judge. We apply this to a variety of categories and target variables (such as trustworthiness in faces and cheapness in art images) and recover both canonical biases and surprising novel priors invisible to direct prompting, warranting further investigation of their downstream effects.
作者Yiming Yang, Valentin Brekke, James Briant, Serge Guillas
Diffusion models generate skillful weather ensembles but require costly iterative sampling. We introduce a supervised energy-distance distillation method that compresses a multi-step diffusion teacher into a single-step student by aligning student forecasts with teacher samples and ground-truth observations. Experiments on global forecasting and typhoon-track prediction show that our student outperforms existing distillation methods and preserves skill for extreme events. It matches or surpasses the teacher across key metrics using only one neural function evaluation per autoregressive step.
展开完整摘要收起摘要↓
Diffusion models generate skillful weather ensembles but require costly iterative sampling. We introduce a supervised energy-distance distillation method that compresses a multi-step diffusion teacher into a single-step student by aligning student forecasts with teacher samples and ground-truth observations. Experiments on global forecasting and typhoon-track prediction show that our student outperforms existing distillation methods and preserves skill for extreme events. It matches or surpasses the teacher across key metrics using only one neural function evaluation per autoregressive step.
作者Junyoung Kim, Hanwen Ren, Lei Zhang, Ahmed H. Qureshi
Multi-agent motion planning for high-degree-of-freedom robotics manipulators in shared workspaces remains a fundamental yet challenging problem. Centralized planners often suffer from poor scalability, while decentralized approaches face robustness and safety concerns. Game-theoretic formulations offer a promising approach for modeling agent interactions, potentially overcoming these limitations. However, their application to articulated multi-arm systems remains limited. This paper presents an iterative Linear Quadratic (LQ) game framework for multi-manipulator motion planning, where each manipulator is modeled as an independent agent optimizing its own objective while interacting with other agents based on shared global states and collision constraints. The method solves a series of local LQ games by linearizing the dynamics and approximating the cost around a nominal trajectory, with Riccati backward recursions yielding feedback Nash strategies. To address the challenges of articulated systems, we incorporate differentiable penalties for self-collision and inter-arm collision into the optimization pipeline, enabling coordinated, collision-aware trajectory generation. Experiments demonstrate that our framework produces smooth, safe, and efficient trajectories in high-dimensional settings, outperforming traditional methods. This highlights the effectiveness of differential game formulations for multi-robot manipulation.
展开完整摘要收起摘要↓
Multi-agent motion planning for high-degree-of-freedom robotics manipulators in shared workspaces remains a fundamental yet challenging problem. Centralized planners often suffer from poor scalability, while decentralized approaches face robustness and safety concerns. Game-theoretic formulations offer a promising approach for modeling agent interactions, potentially overcoming these limitations. However, their application to articulated multi-arm systems remains limited. This paper presents an iterative Linear Quadratic (LQ) game framework for multi-manipulator motion planning, where each manipulator is modeled as an independent agent optimizing its own objective while interacting with other agents based on shared global states and collision constraints. The method solves a series of local LQ games by linearizing the dynamics and approximating the cost around a nominal trajectory, with Riccati backward recursions yielding feedback Nash strategies. To address the challenges of articulated systems, we incorporate differentiable penalties for self-collision and inter-arm collision into the optimization pipeline, enabling coordinated, collision-aware trajectory generation. Experiments demonstrate that our framework produces smooth, safe, and efficient trajectories in high-dimensional settings, outperforming traditional methods. This highlights the effectiveness of differential game formulations for multi-robot manipulation.
作者Seth Carbon, Sierra Moxon, Kimberly Van Auken, Pascale Gaudet, Christopher J. Mungall
Agentic AI has the potential to accelerate curation of biological databases and knowledge bases. However, uptake has been hindered by a number of challenges and obstacles, including access to agents and appropriate training. Here we describe how we have attempted to address and mitigate these challenges and obstacles through the deployment of a cloud-based agentic environment, and the development of an interactive training workshop for the Gene Ontology Consortium. Our cloud environment for agentic-assisted curation was based on the JupyterHub platform, and utilized Claude Code as a universal harness. This allows curators to interact with an agent session through a terminal running in the browser, and has additional benefits such as centralization of access through a single API gateway, removing the need for participants to manage subscriptions or install software locally. We created four training modules, walking participants through basic agentic tool use first and then working up to agentic biological pathway curation using the existing GO-CAM (GO Causal Activity Model) curation tool. Thirty-seven participants took part in the four-hour workshop. Our key takeaway from this workshop is that building community capability with agentic AI is primarily a problem of access, workflow design, and training. Removing technical barriers, introducing capabilities gradually, grounding exercises in familiar curation tasks, and giving curators direct experience evaluating agent output can provide a practical route toward building shared agentic AI capability in distributed scientific communities.
展开完整摘要收起摘要↓
Agentic AI has the potential to accelerate curation of biological databases and knowledge bases. However, uptake has been hindered by a number of challenges and obstacles, including access to agents and appropriate training. Here we describe how we have attempted to address and mitigate these challenges and obstacles through the deployment of a cloud-based agentic environment, and the development of an interactive training workshop for the Gene Ontology Consortium. Our cloud environment for agentic-assisted curation was based on the JupyterHub platform, and utilized Claude Code as a universal harness. This allows curators to interact with an agent session through a terminal running in the browser, and has additional benefits such as centralization of access through a single API gateway, removing the need for participants to manage subscriptions or install software locally. We created four training modules, walking participants through basic agentic tool use first and then working up to agentic biological pathway curation using the existing GO-CAM (GO Causal Activity Model) curation tool. Thirty-seven participants took part in the four-hour workshop. Our key takeaway from this workshop is that building community capability with agentic AI is primarily a problem of access, workflow design, and training. Removing technical barriers, introducing capabilities gradually, grounding exercises in familiar curation tasks, and giving curators direct experience evaluating agent output can provide a practical route toward building shared agentic AI capability in distributed scientific communities.
Standardized benchmarks are often criticized for not being "real workloads," but this critique is rarely backed by data. This paper provides the first systematic, quantitative analysis of the "fidelity gap" between the SPEC CPU2026 suite and its original, upstream open-source counterparts. We compile both the SPEC benchmarks and their upstream applications and execute them with official input workloads under two scenarios: a single-copy latency run and a 192-copy throughput run. Our findings show that most benchmarks exhibit high fidelity in single-copy runs, while a few outliers reveal the impact of SPEC's adaptation process. The multi-copy results further highlight the necessity of this adaptation: several benchmarks become significantly more efficient than their upstream versions under heavy load, underscoring the importance of I/O reduction. This work offers data-driven validation of SPEC's methodology, showing that the fidelity gap is not a flaw but a quantifiable consequence of enforcing portability, determinism, and CPU-centric measurement.
展开完整摘要收起摘要↓
Standardized benchmarks are often criticized for not being "real workloads," but this critique is rarely backed by data. This paper provides the first systematic, quantitative analysis of the "fidelity gap" between the SPEC CPU2026 suite and its original, upstream open-source counterparts. We compile both the SPEC benchmarks and their upstream applications and execute them with official input workloads under two scenarios: a single-copy latency run and a 192-copy throughput run. Our findings show that most benchmarks exhibit high fidelity in single-copy runs, while a few outliers reveal the impact of SPEC's adaptation process. The multi-copy results further highlight the necessity of this adaptation: several benchmarks become significantly more efficient than their upstream versions under heavy load, underscoring the importance of I/O reduction. This work offers data-driven validation of SPEC's methodology, showing that the fidelity gap is not a flaw but a quantifiable consequence of enforcing portability, determinism, and CPU-centric measurement.
Softmax attention stores key and value vectors for every preceding token, causing inference memory to grow with sequence length. Recent language models incorporating Gated DeltaNet (GDN) or Kimi Delta Attention (KDA) reduce this cost by replacing the KV cache in most layers with fixed-size recurrent states. However, these recurrent states are commonly stored in FP32 and consume substantial GPU memory; their updates are memory-bandwidth bound and contribute significantly to decoding latency. To our knowledge, we are the first to study post-training quantization of recurrent states in GDN and KDA based language models. We find that uniform quantization provides a poor accuracy--storage trade-off: INT8 and FP8 already degrade accuracy on complex reasoning tasks, while INT4 and NVFP4 reduce it to near zero. We further find that most quantization-error energy is concentrated in a small subset of channels and that the relative decay strength of state channels remains stable across prompts and tasks. Motivated by these findings, DAMP uses both quantization-error energy and decay-based persistence to identify high-risk channels during offline calibration. It stores these channels at higher precision and the remainder in INT8. We evaluate DAMP on Qwen3.6-35B and Kimi-Linear-48B across six benchmarks covering mathematical reasoning, general reasoning, and code generation. At 9.9 bits per state value, DAMP maintains average accuracy close to the FP32 baseline. DAMP reduces recurrent-state storage by 69.1%, accelerates the recurrent-state update kernel by up to 2.01x, and lowers full-model TPOT by up to 10.9%.
展开完整摘要收起摘要↓
Softmax attention stores key and value vectors for every preceding token, causing inference memory to grow with sequence length. Recent language models incorporating Gated DeltaNet (GDN) or Kimi Delta Attention (KDA) reduce this cost by replacing the KV cache in most layers with fixed-size recurrent states. However, these recurrent states are commonly stored in FP32 and consume substantial GPU memory; their updates are memory-bandwidth bound and contribute significantly to decoding latency. To our knowledge, we are the first to study post-training quantization of recurrent states in GDN and KDA based language models. We find that uniform quantization provides a poor accuracy--storage trade-off: INT8 and FP8 already degrade accuracy on complex reasoning tasks, while INT4 and NVFP4 reduce it to near zero. We further find that most quantization-error energy is concentrated in a small subset of channels and that the relative decay strength of state channels remains stable across prompts and tasks. Motivated by these findings, DAMP uses both quantization-error energy and decay-based persistence to identify high-risk channels during offline calibration. It stores these channels at higher precision and the remainder in INT8. We evaluate DAMP on Qwen3.6-35B and Kimi-Linear-48B across six benchmarks covering mathematical reasoning, general reasoning, and code generation. At 9.9 bits per state value, DAMP maintains average accuracy close to the FP32 baseline. DAMP reduces recurrent-state storage by 69.1%, accelerates the recurrent-state update kernel by up to 2.01x, and lowers full-model TPOT by up to 10.9%.
作者Thomas Nolasque, John Grey, Calista Pham, Ankit Vani
Adding inference structure to a language model lets it search, verify, and revise, but these actions consume the very budget they are supposed to use well. In this paper, we investigate whether there exists a token-budget threshold, below which the overhead of planning and verification hurts performance and above which it helps. We evaluate two systems on FinQA and TAT-QA financial reasoning tasks, using GPT-5.4 mini across 14 budget tiers ranging from 250 to 42,000 output-equivalent tokens. The first system is a monolith, which is a single LLM call. The second is a verified search architecture that adds planning, label-blind checking, and repair capabilities. We run 1,000 cases for a total of 28,000 completed cells. Both systems score 0% at the two lowest tiers, where neither can fit a complete prompt. At 1,000 tokens, the monolith reaches 18% accuracy while verified search scores near 0%, since the planning overhead leaves no room for an answer. From 1,500 tokens onward, verified search surpasses the monolith and maintains a consistent advantage, reaching approximately 44% at the highest tiers while the monolith reaches approximately 40%. The crossover occurs between 1,000 and 1,500 output-equivalent tokens, confirmed by a strict intersection-union test ($p \le 0.001$ at both endpoints).
展开完整摘要收起摘要↓
Adding inference structure to a language model lets it search, verify, and revise, but these actions consume the very budget they are supposed to use well. In this paper, we investigate whether there exists a token-budget threshold, below which the overhead of planning and verification hurts performance and above which it helps. We evaluate two systems on FinQA and TAT-QA financial reasoning tasks, using GPT-5.4 mini across 14 budget tiers ranging from 250 to 42,000 output-equivalent tokens. The first system is a monolith, which is a single LLM call. The second is a verified search architecture that adds planning, label-blind checking, and repair capabilities. We run 1,000 cases for a total of 28,000 completed cells. Both systems score 0% at the two lowest tiers, where neither can fit a complete prompt. At 1,000 tokens, the monolith reaches 18% accuracy while verified search scores near 0%, since the planning overhead leaves no room for an answer. From 1,500 tokens onward, verified search surpasses the monolith and maintains a consistent advantage, reaching approximately 44% at the highest tiers while the monolith reaches approximately 40%. The crossover occurs between 1,000 and 1,500 output-equivalent tokens, confirmed by a strict intersection-union test ($p \le 0.001$ at both endpoints).
作者Eric Yeats, Brendan Kennedy, Loc Truong, John Buckheit, Jung Lee, Jesse Friedbaum, John Emanuello, Henry Kvinge
The hidden states of large language models (LLMs) are known to capture rich information relating to model knowledge and behavior that can be hard to extract from examination of input and output alone. As LLM-based systems increasingly interface with the external world, one area of concern is detecting incorrect or improper use of tools. Motivated by this, we study the effectiveness of using linear probes to detect incorrect tool-calls, measuring probe efficacy across 18 tool-calling LLMs evaluated on the Berkeley Function Calling Leaderboard. Overall, we find that probing is an effective means to catch a range of different tool-calling errors, including errors arising from using an argument that has the wrong value but the correct type, which might not be recorded by standard logging frameworks. Important factors in success include model size, probing layer, and model post-training type. We also show that probes are capable of generalizing to novel types of errors, which is critical in real world deployments.
展开完整摘要收起摘要↓
The hidden states of large language models (LLMs) are known to capture rich information relating to model knowledge and behavior that can be hard to extract from examination of input and output alone. As LLM-based systems increasingly interface with the external world, one area of concern is detecting incorrect or improper use of tools. Motivated by this, we study the effectiveness of using linear probes to detect incorrect tool-calls, measuring probe efficacy across 18 tool-calling LLMs evaluated on the Berkeley Function Calling Leaderboard. Overall, we find that probing is an effective means to catch a range of different tool-calling errors, including errors arising from using an argument that has the wrong value but the correct type, which might not be recorded by standard logging frameworks. Important factors in success include model size, probing layer, and model post-training type. We also show that probes are capable of generalizing to novel types of errors, which is critical in real world deployments.
Vision-language-action models (VLAs) have shown strong promise for general-purpose robotic manipulation by mapping language instructions and vision observations directly to actions. However, most VLAs primarily condition action prediction on current observations and lack an explicit mechanism for reasoning over future task dynamics, which is particularly important for fine-grained, contact-rich manipulation. We present PHR-VLA, a framework that enables planning-horizon reasoning in VLAs through privileged latent representations of future dynamics. PHR-VLA introduces a lightweight auxiliary future head that, during training, aligns the VLA's internal representations with latent dynamics extracted from future observations. Evaluation results demonstrate that local, contact-centric, patch-level latent dynamics supervision from the wrist camera improves success rate on LIBERO from 84.1% to 88.4% and on real-world disassembly tasks from 63.3% to 82.5%. Patch-level supervision from a third-person camera also improves performance on Meta-World from 56.70% to 57.8%. These results demonstrate that privileged latent dynamics alignment provides an effective training signal for improving anticipatory reasoning in VLA policies. Project website: \href{https://davoodsz.github.io/PHR-VLA.github.io/}{https://davoodsz.github.io/PHR-VLA.github.io/}
展开完整摘要收起摘要↓
Vision-language-action models (VLAs) have shown strong promise for general-purpose robotic manipulation by mapping language instructions and vision observations directly to actions. However, most VLAs primarily condition action prediction on current observations and lack an explicit mechanism for reasoning over future task dynamics, which is particularly important for fine-grained, contact-rich manipulation. We present PHR-VLA, a framework that enables planning-horizon reasoning in VLAs through privileged latent representations of future dynamics. PHR-VLA introduces a lightweight auxiliary future head that, during training, aligns the VLA's internal representations with latent dynamics extracted from future observations. Evaluation results demonstrate that local, contact-centric, patch-level latent dynamics supervision from the wrist camera improves success rate on LIBERO from 84.1% to 88.4% and on real-world disassembly tasks from 63.3% to 82.5%. Patch-level supervision from a third-person camera also improves performance on Meta-World from 56.70% to 57.8%. These results demonstrate that privileged latent dynamics alignment provides an effective training signal for improving anticipatory reasoning in VLA policies. Project website: \href{https://davoodsz.github.io/PHR-VLA.github.io/}{https://davoodsz.github.io/PHR-VLA.github.io/}
We study audio-visual conflict as a compositional generalization test for AV-LLMs: the model must combine synchronized but semantically incompatible audio and video evidence and decide whether the pair matches. On VideoLLaMA 2-7B-AV, three alignment configurations remain nearchance on the scored exact-string Yes/No subset of AVHBench, even though their output priors shift substantially. Similarly, off-the-shelf InternVideo2 experienced a 32.3% accuracy decrease specifically under cross-modal conflict, accompanied by a 17.3% instruction-following failure. We call this failure mode prior dominance: late-layer commitment to an internally preferred answer pattern that is weakly grounded in the conflicting inputs. To explain this behavior, we conduct a mechanistic interpretability analysis and find that commitment remains concentrated at 25.5 $\pm$ 1 layers. We show that stronger temporal alignment changes answer bias, but do not improve compositional conflict resolution. Code and data to reproduce our mechanistic audit and behavioral evaluations are available at https://github.com/AdarshSudheer09/AVHBench-dmai.
展开完整摘要收起摘要↓
We study audio-visual conflict as a compositional generalization test for AV-LLMs: the model must combine synchronized but semantically incompatible audio and video evidence and decide whether the pair matches. On VideoLLaMA 2-7B-AV, three alignment configurations remain nearchance on the scored exact-string Yes/No subset of AVHBench, even though their output priors shift substantially. Similarly, off-the-shelf InternVideo2 experienced a 32.3% accuracy decrease specifically under cross-modal conflict, accompanied by a 17.3% instruction-following failure. We call this failure mode prior dominance: late-layer commitment to an internally preferred answer pattern that is weakly grounded in the conflicting inputs. To explain this behavior, we conduct a mechanistic interpretability analysis and find that commitment remains concentrated at 25.5 $\pm$ 1 layers. We show that stronger temporal alignment changes answer bias, but do not improve compositional conflict resolution. Code and data to reproduce our mechanistic audit and behavioral evaluations are available at https://github.com/AdarshSudheer09/AVHBench-dmai.
作者Jonysberg Quintino, Hermano Moura, Filipe Calegário
Integrating Large Language Models (LLMs) into the Software Development Life Cycle (SDLC) can improve developer productivity, but it also introduces security, privacy, and compliance risks during model selection. Regulations and frameworks such as the EU AI Act, the NIST AI Risk Management Framework (RMF), the General Data Protection Regulation (GDPR), the Lei Geral de Proteção de Dados (LGPD), and ISO/IEC 42001 establish obligations that are often difficult to translate into operational criteria for technical decision-making. This paper proposes a model to support governance and compliance in LLM selection for software engineering projects. The model is developed through Design Science Research (DSR) and is structured in three layers: (i) regulatory requirements, (ii) organizational governance capabilities, instantiated by a multi-criteria decision matrix with knock-out and weighted scoring criteria, and (iii) productivity and sustainability outcomes, operationalized by the LLM governance assessment protocol (PAG-LLM). A regulatory feedback loop connects operational results back to the normative layer, enabling iterative refinement of the model. A pilot evaluation with 20 adversarial scenarios based on Common Weakness Enumeration (CWE) and the OWASP Top 10 suggests distinct risk profiles between commercial cloud-based LLMs and local open-source LLMs. The results provide preliminary evidence that regulatory disqualification logic, particularly K.O. criteria, can prevent the selection of technically competitive models that nonetheless pose unacceptable compliance risks, demonstrating the feasibility of governance-oriented LLM selection in software engineering projects.
展开完整摘要收起摘要↓
Integrating Large Language Models (LLMs) into the Software Development Life Cycle (SDLC) can improve developer productivity, but it also introduces security, privacy, and compliance risks during model selection. Regulations and frameworks such as the EU AI Act, the NIST AI Risk Management Framework (RMF), the General Data Protection Regulation (GDPR), the Lei Geral de Proteção de Dados (LGPD), and ISO/IEC 42001 establish obligations that are often difficult to translate into operational criteria for technical decision-making. This paper proposes a model to support governance and compliance in LLM selection for software engineering projects. The model is developed through Design Science Research (DSR) and is structured in three layers: (i) regulatory requirements, (ii) organizational governance capabilities, instantiated by a multi-criteria decision matrix with knock-out and weighted scoring criteria, and (iii) productivity and sustainability outcomes, operationalized by the LLM governance assessment protocol (PAG-LLM). A regulatory feedback loop connects operational results back to the normative layer, enabling iterative refinement of the model. A pilot evaluation with 20 adversarial scenarios based on Common Weakness Enumeration (CWE) and the OWASP Top 10 suggests distinct risk profiles between commercial cloud-based LLMs and local open-source LLMs. The results provide preliminary evidence that regulatory disqualification logic, particularly K.O. criteria, can prevent the selection of technically competitive models that nonetheless pose unacceptable compliance risks, demonstrating the feasibility of governance-oriented LLM selection in software engineering projects.
作者Tianxiang Pan, Baitao Gong, Mo Guang, Hongwei Yong, Tianpeng Jiang, Yaqian Li, Zheng Cao, Kaiwen Long
Diffusion-based language models (dLLMs) enable parallel token generation through iterative denoising, but existing decoding strategies collapse to single-token generation under low confidence, severely limiting throughput. Unlike autoregressive models where speculative decoding operates on token sequences in a fixed left-to-right order, dLLMs require speculating over denoising trajectories-sequences of multi-token updates with explicit positions and unmasking orders. We develop a trajectory-level speculative framework that constructs draft denoising trajectories via confidence-stratified tree exploration and verifies them through blockwise parallel evaluation with bidirectional attention masking. Our method further introduces inter-block speculation, exploiting diffusion models' bidirectional structure to perform cross-block lookahead. We formally characterize when this approach is exact and identify trajectory drift as the fundamental cost of increased parallelism. Building on Fast-dLLM's dual-cache infrastructure, our framework reduces denoising iterations by 30-40% and increases tokens-per-step from 2.6 to 4.3, achieving 7-14x speedup over vanilla dLLMs and 1.3x over Fast-dLLM with less than 1% accuracy change across reasoning and code benchmarks.
展开完整摘要收起摘要↓
Diffusion-based language models (dLLMs) enable parallel token generation through iterative denoising, but existing decoding strategies collapse to single-token generation under low confidence, severely limiting throughput. Unlike autoregressive models where speculative decoding operates on token sequences in a fixed left-to-right order, dLLMs require speculating over denoising trajectories-sequences of multi-token updates with explicit positions and unmasking orders. We develop a trajectory-level speculative framework that constructs draft denoising trajectories via confidence-stratified tree exploration and verifies them through blockwise parallel evaluation with bidirectional attention masking. Our method further introduces inter-block speculation, exploiting diffusion models' bidirectional structure to perform cross-block lookahead. We formally characterize when this approach is exact and identify trajectory drift as the fundamental cost of increased parallelism. Building on Fast-dLLM's dual-cache infrastructure, our framework reduces denoising iterations by 30-40% and increases tokens-per-step from 2.6 to 4.3, achieving 7-14x speedup over vanilla dLLMs and 1.3x over Fast-dLLM with less than 1% accuracy change across reasoning and code benchmarks.
Mathematical reasoning has seen rapid progress in large language models (LLMs), yet existing methods optimize predominantly for final-answer correctness, raising the question whether models truly internalize mathematical concepts or merely memorize solution patterns. In human mathematics education, example-based reasoning such as constructing counterexamples to test theorem boundaries reflects deep conceptual understanding, but remains underdeveloped in current LLMs. Enhancing this capability through preference optimization presents two key challenges: (1) the model's limited example-based reasoning ability makes constructing effective preference pairs inherently difficult; and (2) capability acquisition is progressive, as the model must first learn to adopt this strategy before learning to apply it correctly. Therefore we propose INSPIRE, an Internalize-Then-Improve approach combining Reference-Guided Student Internalization (RGSI), which produces high-quality preference candidates under the policy model's own distribution, with a stage-wise rubric preference training strategy that decomposes learning into method-oriented and correctness-oriented stages. Experiments across multiple model scales and families demonstrate consistent improvements, even surpassing larger open-source models, while evaluations on out-of-distribution benchmarks confirm no degradation in general mathematical reasoning ability.
展开完整摘要收起摘要↓
Mathematical reasoning has seen rapid progress in large language models (LLMs), yet existing methods optimize predominantly for final-answer correctness, raising the question whether models truly internalize mathematical concepts or merely memorize solution patterns. In human mathematics education, example-based reasoning such as constructing counterexamples to test theorem boundaries reflects deep conceptual understanding, but remains underdeveloped in current LLMs. Enhancing this capability through preference optimization presents two key challenges: (1) the model's limited example-based reasoning ability makes constructing effective preference pairs inherently difficult; and (2) capability acquisition is progressive, as the model must first learn to adopt this strategy before learning to apply it correctly. Therefore we propose INSPIRE, an Internalize-Then-Improve approach combining Reference-Guided Student Internalization (RGSI), which produces high-quality preference candidates under the policy model's own distribution, with a stage-wise rubric preference training strategy that decomposes learning into method-oriented and correctness-oriented stages. Experiments across multiple model scales and families demonstrate consistent improvements, even surpassing larger open-source models, while evaluations on out-of-distribution benchmarks confirm no degradation in general mathematical reasoning ability.
Determining whether large language models derive answers from context or prior knowledge remains a fundamental challenge. Self-contained linguistic olympiad puzzles provide a controlled setting where all answers derive solely from expert-designed context examples without external knowledge. Removing individual context examples can eliminate information needed for specific questions while leaving the rest of the puzzle unchanged. We leverage this to introduce a diagnostic framework for analyzing individual context examples. Using 53 UK Linguistics Olympiad puzzles, we generate two modified variants by deleting a single context example: (1) uniform random deletion, and (2) targeted deletion (inspired by error-correcting codes) to remove a structurally load-bearing example uniquely carrying necessary information. We formalize this impact using a Question Damage Score to classify puzzles as fragile or robust. Evaluating three frontier LLMs under instructions to abstain when information is insufficient, we find they rarely abstain, often continuing to produce correct answers after load-bearing context is removed. These findings motivate further investigation into context-based reasoning, prior knowledge, memorization, and linguistic inference. Beyond abstention, the framework enables fine-grained analyses of context reliance, including causal interventions, stopping-set analysis, targeted contamination studies, and mechanistic interpretability.
展开完整摘要收起摘要↓
Determining whether large language models derive answers from context or prior knowledge remains a fundamental challenge. Self-contained linguistic olympiad puzzles provide a controlled setting where all answers derive solely from expert-designed context examples without external knowledge. Removing individual context examples can eliminate information needed for specific questions while leaving the rest of the puzzle unchanged. We leverage this to introduce a diagnostic framework for analyzing individual context examples. Using 53 UK Linguistics Olympiad puzzles, we generate two modified variants by deleting a single context example: (1) uniform random deletion, and (2) targeted deletion (inspired by error-correcting codes) to remove a structurally load-bearing example uniquely carrying necessary information. We formalize this impact using a Question Damage Score to classify puzzles as fragile or robust. Evaluating three frontier LLMs under instructions to abstain when information is insufficient, we find they rarely abstain, often continuing to produce correct answers after load-bearing context is removed. These findings motivate further investigation into context-based reasoning, prior knowledge, memorization, and linguistic inference. Beyond abstention, the framework enables fine-grained analyses of context reliance, including causal interventions, stopping-set analysis, targeted contamination studies, and mechanistic interpretability.