每天知道
你的领域
出了什么

This work provides an overview of the different strategies that can be used to evaluate the performance of AI models and agents based on large language models (LLMs) for materials synthesis. After providing a brief overview of the key technologies behind the current generation of AI agents based on LLMs, we summarize the different approaches to evaluating these models in the context of materials science and in particular on materials synthesis, with a specific emphasis on scenarios in which the models are directly integrated with experimental tools. We discuss evaluation strategies spanning knowledge and reasoning benchmarks, tool-use benchmarks, and closed loop benchmarks involving the interaction with experimental systems or realistic virtual tools. We use atomic layer deposition (ALD) as a case study, emphasizing how existing approaches in the literature both build from general approaches used beyond materials science and can be generalized to other materials synthesis techniques. Finally, we provide a practical evaluation framework to evaluate LLMs in the context of materials synthesis

Enterprise data agents answer business queries by chaining many tool calls over multiple reasoning steps, routinely accumulating hundreds of thousands of context tokens per session. Existing compression strategies typically allocate retention budgets without accounting for the downstream consequences of removing individual tool outputs. Aggressive compression may therefore trigger costly tool re-invocations that offset the initial savings. We call this the compression--consequence gap. To close it, we propose TRACER, which formulates compression as a sequential per-tool decision problem. A lightweight REINFORCE policy assigns query-conditioned retention ratios using only information available at each compression event. Its consequence-aware objective jointly accounts for task success, total token consumption, and post-compression tool re-invocations. To improve credit assignment, TRACER uses a learned outcome model to compare the predicted consequences of the selected retention ratio with those of fully retaining each tool output. On held-out production queries across three compressor backends, TRACER reduces total token consumption by 29--46% relative to keeping all context while maintaining comparable or higher task success. Compared with a tool-type-conditional static policy, TRACER provides an additional 15--18% of token savings. Interventional rollouts show that the learned per-tool credit scores correlate with measured single-tool consequences. The learned policy also yields positive savings when transferred across agent backbones and compressor architectures, and reduces token consumption by 18--25% on five held-out LOCA-bench environments. These results demonstrate the value of consequence-aware, per-tool context retention for improving the efficiency of long-horizon language agents.

A language-guided robot operating in a real kitchen must do more than produce a plan that appears correct. It must also execute that plan safely in cluttered environments under imperfect perception. Large language models (LLM) can decompose instructions into action sequences, yet a language-action gap remains: a plan may appear valid linguistically while being physically infeasible under kinematic and collision constraints. We bridge this gap by formalizing the reasoning-execution boundary as a typed contract. From RGB-D observations, the system grounds perceived objects in an explicit, collision-aware scene model and constrains language-level decisions through schema-validated tool calls defined by the Model Context Protocol (MCP), rejecting malformed commands before they reach the robot. Each validated call is deterministically grounded in a MoveIt Task Constructor pipeline, where candidate motions are evaluated against the reconstructed planning scene in a verify-then-act step. Only trajectories that pass both kinematic and collision checks are sent to the robot. On a physical UFactory 850, the method achieves up to 80% success across ten trials per task on pouring tasks involving liquids, granular media, and discrete solids. It achieves 90% success on a grasp-and-place task using the same planning, protocol, and verification stack. Although a scripted policy slightly outperforms our method on the easiest task, its success rate falls to 10% on the hardest, compared with 60% for our method.

Several works have investigated the influence of graph topology on cooperation among artificial agents, while the majority of the literature has focused on modelling agents' adaptation through strategy imitation, which relies solely on the cumulative payoffs of others. This paper investigates scenarios in which each agent learns to play the two-player Iterated Prisoner's Dilemma (IPD) using deep reinforcement learning. Each agent is represented as a node in a graph, where its neighbours constitute the pool of opponents with whom it can interact. During each IPD episode, agents are provided with different types of information about their opponent, consisting of action history and opponent identity. Experimental results across different graph topologies show that the number of neighbours per node and the average path length are the main factors affecting the emergence of cooperation. We also show that, while partner selection fosters mutual cooperation by limiting the diversity of the opponent pool, providing agents with the identity of their opponent hinders the proliferation of cooperative strategies.

Large language models (LLMs) have demonstrated considerable promise in program generation for small-scale and conventional application development; however, they remain limited when applied to complex, domain-specific tasks such as medical image processing. General-purpose models lack explicit domain knowledge and robust validation mechanisms to ensure correctness, often requiring substantial human intervention to produce reliable processing pipelines. To address these limitations, we propose AutoMedImg, a multi-agent framework for fully automated medical image processing code generation. AutoMedImg orchestrates specialised agents across two phases: a Planning Phase that performs dataset analysis and architecture design with semantic and formal verification, and a Coding Phase that generates modules in parallel with static checking, execution testing, and assembly validation. This multi-stage validation mitigates error propagation throughout generation, while comprehensive auto-context engineering combining domain-specific knowledge bases, shared memory, and validation feedback automates context construction without manual prompting. A cross-project adaptive pipeline synthesis mechanism further accumulates validated pipelines and retrieves proven components for new tasks based on project similarity, enhancing generation efficiency through cross-project learning. Extensive evaluation across six diverse and well-established medical imaging datasets with five backbone LLMs demonstrates that AutoMedImg achieves zero human intervention, with Dice scores of up to 0.90 for segmentation tasks and 99% accuracy for classification.

The ongoing changes in software engineering requirements have created a substantial need for automated tools which can create secure source code from natural language input. The performance of traditional Large Language Models (LLMs) becomes limited by their "one-shot" capability which results in logical hallucinations together with reduced algorithmic performance during complicated operations. The research presents an autonomous AI Coding Agent which establishes a connection between LLM-generated content and production-ready software through its organized methodology for decision making. Our framework uses the Gemini 2.5 Flash API for essential reasoning capabilities while employing a tailored Monte Carlo Tree Search (MCTS) method to solve code generation challenges as a search operation. The agent uses a "Self-Critic" evaluator system to test different implementation methods which it ranks according to their accuracy and difficulty level before it improves its operational framework through backpropagation. The system operates through a Flask-based web interface which delivers instant feedback together with syntax highlighting features. Our experimental results show that the MCTS-based method achieves a 92% success rate on complex logical prompts while surpassing standard zero-shot generation models.

Multimodal search agents answer visual questions by interleaving image understanding, web retrieval, tool use, and evidence synthesis. Strong systems exist, but in two expensive regimes: proprietary frontier models such as GPT-5 and Gemini, or large open vision-language backbones trained with substantial agentic data and reinforcement learning. We ask a different question: when released agent trajectories are distilled into much smaller backbones under a single-node budget, what is actually transferred? We study this with LiteSearch-VL, a low-compute recipe for Qwen3-VL-2B and Qwen3-VL-4B that uses only released OpenSearch-VL trajectories, parameter-efficient LoRA adapters, and synthetic step-level preferences: DPO on GPT-5-generated hard negatives targeting five local failure modes (premature answer, wrong tool, weak query, repeated query, ignored image). Across 12,400 GPT-5-judged rollouts on SimpleVQA, FVQA, LiveVQA, and VDR-Bench-testmini, the dominant effect is behavioral rather than a uniform accuracy lift: full-trajectory supervised fine-tuning transfers the agent contract, taking the 2B model from almost never emitting a usable answer (1,237/1,240 no_answer rollouts) to 28.4% macro Pass@1, matching or slightly exceeding the off-the-shelf 4B base (25.6%). Synthetic preference learning and compact tool distillation act as refinements rather than phase transitions (best 4B configuration: 30.8% macro Pass@1). Finally, a controlled VDR step-budget ablation shows that extra search turns convert abstentions into wrong_entity errors rather than correct answers, identifying answer verification, not search depth, as the next bottleneck for small multimodal agents.

Multi-agent LLM systems often coordinate by compressing an upstream interaction into a handoff artifact that downstream agents treat as shared state. We show that this handoff step is a structural source of privacy leakage: summaries preferentially preserve operational facts while weakening the boundary metadata that governs how those facts may be used---a failure mode we call summary collapse. On a controlled multi-agent coordination testbed we measure marker survival with a human-validated judge ($κ= 0.74$), where $σ_b = 1$ means every boundary marker survives verbatim and $σ_b = 0$ means all are lost. Boundary-marker and operational-fact survival are nearly uncorrelated at the handoff level on both GPT-5-mini and DeepSeek-R1-32B (Pearson $r$ near zero): uncompressed free-text handoffs preserve boundaries at $σ_b \approx 0.80$, whereas a $25$-word budget drops $σ_b$ to ${\approx}0.57$ while operational-fact survival stays near ceiling. Controlled downstream tests reveal that protection depends on boundary explicitness: vague languages leak in $73%$ of GPT and $50%$ of DeepSeek cases, while explicit constraints reduce leakage to under $15%$ across all three tested models. A no-handoff single-agent control further shows the failure is not reducible to multi-agent topology as direct full-marker access still leaks more often than the operationalized handoff. Prompt-only mitigation and exact-string redaction only partially address the problem, while a gold-derived audience allowlist nearly eliminates leakage across models, showing that correctly identifying audience boundaries is the key factor.

Large language model (LLM) agents have demonstrated remarkable proficiency in manually constructed environments, yet their performance frequently collapses when transitioned to complex real-world settings. Existing research largely attribute this degradation to the compositional generalization gaps in LLMs on combinations of multiple simple, well-structured environments. In this work, we propose that LLM web agents can learn simple environment observations at test time. Specifically, we introduce trial steps for agents to decompose a complex environment observation into sub-modules, and implement a label-free learning method, Test-Time Environment Decomposition (TTED), to adapt agent behaviors with experience during inference. Our empirical evaluations demonstrate the framework's efficacy across both synthetic and realistic benchmarks, showing (1) experience gains acquired within simpler sub-environments can be effectively composed to improve performance in the full one, and (2) test-time training on sub-environments can significantly enhance the compositional generalization of agents in real-world web automation tasks. We also provide key insights in the design of the label-free learning algorithm. As more complex environments are accessed by LLM agents, we believe learning environment decomposition skills at test time will be critical for robust real-world deployment.

Tool-use benchmarks generally evaluate whether an agent completes a workflow using appropriate tools and valid arguments. However, feasibility alone is insufficient in real-world decision settings such as route planning and fleet dispatch. Individual choices interact through shared constraints and costs, so a feasible solution may still be substantially suboptimal. This raises a harder question: can an agent turn information gathered through tools into a globally optimal decision? We introduce AlgoWorlds, a benchmark that transforms formally specified combinatorial optimization problems into partially observed decision environments with verifiable global optima. Each environment contains a hidden instance observed only through task-specific information tools, after which the agent commits to one structured decision evaluated for feasibility and optimality. AlgoWorlds contains 240 environments covering ten combinatorial optimization families and four workload levels. Family-specific deterministic programs generate the instances, exact algorithms certify their optima and determine workload levels, and two structurally different tool interfaces present each underlying instance. We evaluate seven leading LLMs, including Claude Opus 4.8 and GPT-5.6 Sol. Achieving global optimality remains highly challenging: although leading models produce feasible decisions in most cases, the best-performing model reaches exact optimality in only 38.61% of cases. Even when agents collect sufficient information to reconstruct the hidden instance, most failures end in feasible but suboptimal decisions. The challenge therefore extends beyond information acquisition to information integration, global constraint reasoning, and decision verification. The project homepage is available at https://xzx34.github.io/AlgoWorlds/, and the code is available at https://github.com/xzx34/AlgoWorlds.

Piecewise-linear (PWL) optimization problems arise in many mixed-integer programming (MIP) optimization applications, including portfolio optimization, workforce scheduling, and resource allocation. But solving them to global optimality remains computationally expensive because branch-and-bound repeatedly solves LP relaxation subproblems. Existing solvers are largely CPU-centric, leaving the scalability of modern GPUs underutilized. Few prior GPU-accelerated branch-and-bound either targets neural network which is not suitable for general PWL optimization, or accelerates only auxiliary subroutines such as strong branching heuristics within CPU-centric MIP solvers. To bridge this gap, we propose B$^3$-PWL, a GPU-centric batched branch-and-bound framework for piecewise-linear optimization with Special Ordered Set of type 2 (SOS2) constraints. Our method solves batches of LP relaxation subproblems concurrently on the GPU using a first-order primal-dual solver, enabled by a specialized batched block-tiled sparse matrix kernel. To complement bound computation, we further introduce a unified feasibility search module that combines an SOS2 repair primal heuristic with a batched feasibility pump to rapidly obtain feasible incumbents and improve pruning efficiency. On a benchmark of 43 PWL-MIP instances, B$^3$-PWL achieves a 9.25x geometric-mean speedup over NVIDIA cuOpt while reaching high-quality feasible incumbents on every tested instance. On a public valve-point unit-commitment benchmark, it further outperforms NVIDIA cuOpt and the open-source CPU solvers SCIP and HiGHS, demonstrating the potential of first-order LP methods as the central engine of GPU-accelerated branch-and-bound.

Large Language Models (LLMs) often suffer from hallucination and struggle with complex reasoning tasks requiring multi-hop domain knowledge. While integrating Knowledge Graphs (KGs) provides a structured and verifiable information source, current KG-enhanced LLM paradigms usually rely on single-agent path extraction and fixed prompting, lacking adaptability and facing huge search spaces. To address these challenges, we propose RACER, a Reinforced Agent Collaboration framework for Explainable Reasoning on knowledge graphs. RACER employs a semantic-aware action pruning and teacher-guided reinforcement learning mechanism to efficiently extract high-quality reasoning pathways from large-scale KGs. Furthermore, to mitigate single-path generation pitfalls, we introduce a cross-task accumulated shared memory graph paired with an attention-driven multi-path knowledge refinement module. Finally, RACER orchestrates these components through a four-role multi-agent collaboration system (GraphAgent, TemplateAgent, AnswerAgent, and CriticAgent) to dynamically refine prompts and evaluate answers. Extensive experiments on CommonsenseQA and OpenBookQA datasets demonstrate that RACER significantly outperforms state-of-the-art KG-enhanced LLM baselines with an average improvement of 5%, offering robust and highly interpretable reasoning capabilities.

Semantic Search on LinkedIn must retrieve relevant profiles from a corpus of hundreds of millions in response to natural-language queries such as "a fintech founder in Berlin who worked in payments." The deployed relevance policy is bottleneck-oriented: every active non-negotiable facet must be satisfied, and a pre-existing LLM Graded Relevance (GR) judge operationalizes this through a fixed min/median aggregation over facet grades. Cosine similarity instead averages evidence, letting a strong match on one facet mask failure on another, capping the recall of the first-stage (L0) retriever. We present a policy-aligned retrieval framework: embeddings are partitioned into eight category-supervised segments whose scores follow the same min/median rule at serving time; for multi-vector retrieval, this segment score is computed independently per tagged document slot and maximized across slots. A lightweight single-slot Stage-1 scorer generates high-recall candidates, while scale-invariant relative-norm gating keeps category activation consistent across training, evaluation, and serving. On 21K held-out queries, this representation improves offline relevance over a matched-capacity baseline, with gains broadly distributed across facet combinations. We serve this framework with a two-stage GPU architecture: an FP8 coarse ranker scores the full corpus, increasing per-shard capacity by 71% and Stage-1 matmul throughput by 36%, then an FP16 stage exactly re-ranks an oversampled candidate set, recovering 99.6-99.8% of full-FP16 recall at over 500 QPS per shard replica. In a member-randomized A/B test, exploratory-query Precision@10 under the unchanged GR judge rises from 63.7% to 79.0% and navigational Precision@1 from 65.5% to 74.7%, with a blinded human evaluation independently confirming the Precision@10 gain.

Unified multimodal models jointly support understanding and generation, but incur substantial redundant computation across tokens, layers, and generation timesteps. Through token-importance probing, we identify an asymmetric core-expansion structure: understanding exhibits a stable importance component, while generation largely shares this component but requires progress-dependent corrections. We therefore propose CE-Router, which uses a task-shared core scorer and progress-conditioned generation expansions, optimized through generation decomposition and cross-task core alignment. At inference, CE-Router compacts token computation and supplies a learned routing signal to Unified Computation Scheduling, which coordinates layer skipping, FFN pruning, diffusion-head cache reuse, and denoising-step early exit. Experiments on two representative UMM architectures demonstrate consistent quality--efficiency improvements across both tasks, retaining 98.03% of dense understanding performance with a 1.93$\times$ end-to-end inference speedup.

Artificial Intelligence-Generated Content (AIGC) services employ Generative AI (GenAI) models to automatically generate diverse content. Mobile AIGC networks host GenAI models on edge-located AIGC Service Providers (ASPs) to deliver low-latency and personalized AIGC services for mobile users. However, AIGC inference tasks typically occupy GPU memory until task completion, causing GPU memory exhaustion at serving ASPs and triggering out-of-memory failures rather than merely increasing service latency. Existing studies on AIGC task orchestration have largely overlooked GPU memory feasibility constraints. To address this issue, we develop a cooperative multi-agent orchestration framework, in which each edge node is equipped with a scheduling agent to route tasks to local ASPs or neighboring edge nodes. Since scheduling agents make decisions based only on local observations, while peer offloading couples their resource states and long-term utilities, we formulate the orchestration process as a cooperative Decentralized Partially Observable Markov Decision Process (Dec-POMDP). To solve the Dec-POMDP, we propose an \underline{A}ttention-guided \underline{M}ulti-\underline{A}gent deep reinforcement learning algorithm with \underline{Diff}usion policies (A-MADiff) under the centralized training with a decentralized execution paradigm. A-MADiff employs diffusion-based decentralized actors to generate multi-modal preferences over feasible orchestration actions, and an attention-guided centralized critic to estimate per-agent values from cross-agent states under GPU memory heterogeneity. Numerical results demonstrate that A-MADiff significantly improves the cumulative reward over the state-of-the-art baseline.

Diffusion-based visual generative models deliver strong image and video synthesis quality but incur high inference costs because sequential samplers repeatedly evaluate large networks. Caching-based methods reduce inference latency by reusing intermediate computations across adjacent timesteps. However, existing cache controllers rely primarily on local temporal variation and overlook the trajectory-level consequences of cache reuse. We introduce Error-Propagation-Aware Cache (EpaCache), a training-free caching policy that adaptively allocates the reuse budget on timesteps with lower downstream impact. Experiments on image and video synthesis models demonstrate that EpaCache consistently improves the latency--fidelity trade-off over existing caching methods. On FLUX.1-dev, EpaCache outperforms the prior state-of-the-art caching method in both latency and fidelity, reducing inference time from $11.7$ s to $11.3$ s while improving PSNR from $21.4$ to $22.8$. On HunyuanVideo, EpaCache achieves a $2.63\times$ speedup over uncached inference and improves SSIM from $0.891$ to $0.905$ over the prior state-of-the-art method at matched latency.

Dynamic sparse attention can reduce the quadratic cost of long-context prefilling without changing model weights. MInference assigns each attention head one pattern offline and estimates that pattern's sparse indices for every prompt. This design is efficient, but it assumes that a head's preferred pattern and sparsity budget remain suitable across inputs. We introduce RouteSparse, which routes each head and prompt segment among a small library of GPU-efficient sparse patterns. A low-cost probe estimates pattern utility and uncertainty; a latency-aware router then selects a pattern and budget, while uncertain cases fall back to a denser mask. We formulate routing as constrained risk minimization, derive an attention-output error certificate from omitted probability mass, and evaluate the method on long-context retrieval, question answering, summarization, and language modeling. On Llama 3.1-8B-Instruct with 128K-token prompts, RouteSparse achieves $6.5\times$ dense prefill speed with a 0.2-point RULER drop relative to dense attention, compared with $7.3\times$ speed and a 1.6-point drop for fixed per-head routing. Ablations confirm that input-conditional routing, hardware profiling, and selective dense fallback each contribute to the quality--latency tradeoff.

Sparse computations are fundamental to scientific computing, graph analytics, and machine learning, yet their performance is highly sensitive to the diverse sparsity and patterns. This is because cache reuse, memory coalescing, and load balancing depend critically on the sparsity patterns. This work gives the first known exploration of the connections between sparse matrix computation and spectral analysis by treating sparse matrices as two-dimensional signals and analyzing their frequency-domain representations through Fast Fourier Transform. We show that spectral signatures uncover global structural characteristics that are not sufficiently captured by conventional spatial statistics and provide complementary information for understanding sparse computation performance. Experiments on incorporating spectral features into machine-learning-based SpMV format selection demonstrate the usefulness of such spectral analysis over a state-of-the-art spatial-only model. By uncovering the principled connections between spectral characteristics and sparse matrix computations, this work introduces a novel analytical perspective into sparse computation, and provides a new approach to enhancing the current sparse structure characterization and optimization. On pruned LLM decoding, adding spectral features improves kernel selection and yields 1.035--1.245$\times$ kernel speedups.

Spherical Transformers have emerged as a promising framework for panoramic semantic segmentation (PASS) by operating directly on spherical geometry and alleviating projection-induced distortions. However, existing architectures often assume canonical spherical structure and stable viewpoints, which are frequently violated in real-world imagery due to unconstrained camera motion, introducing contextual and geometric ambiguity. Consequently, they lack adaptive mechanisms to handle such ambiguity, limiting robustness to unseen spherical transformations. In contrast, biological perception is inherently ambiguity-aware, adapting to fluctuations in cue reliability caused by geometric and contextual variations to maintain stable interpretation under complex transformations. Motivated by this, we first systematically analyze existing PASS architectures under various unseen spherical transformations. We then introduce AdapToPASS, a novel bio-inspired Spherical Transformer that adaptively models contextual and geometric ambiguities for robust PASS. At its core, Adaptive Spherical Attention (AdaSpA) blocks dynamically modulate attention according to local contextual ambiguity, mimicking adaptive, context-driven biological perception. To address geometric ambiguity, AdapToPASS employs Bifocal Spherical Representation to balance field of view and spatial resolution, together with boundary supervision inspired by the boundary-sensitive nature of biological vision. Across indoor and outdoor semantic segmentation, AdapToPASS consistently outperforms prior state-of-the-art methods. Under unseen spherical transformations, it surpasses the next-best method by +13.38% relative mIoU on Stanford2D3D and +18.77% on WildPASS. We further introduce AdapToPASS-Swift, a lightweight variant with fewer than 2M parameters, which surpasses compact baselines while retaining robustness to spherical transformations.

Classic Formal Concept Analysis (FCA) primarily focuses on the positive relationships between objects and attributes and does not have mechanisms for handling negation.To overcome this limitation, we introduce three types of negation concepts (contradictory negation, opposite negation, intermediary negation) into FCA.Based on the set SCOI and logic LCOI+PLCOI with these three types negation, we define formal context, Galois connection operators, formal concept and concept lattice with three types of negation,this leads to the proposal of a FCACOI: Formal Concept Analysis with contradictory negation, opposite negation and intermediary negation.For the reasoning in FCACOI, this paper focuses on attribute implication reasoning. Based on the logic LCOI+PLCOI and its semantics, we introduce the notion of ICOI-entailment as the semantic implication for attribute implication reasoning in FCACOI. Through ICOI-entailment, a connection is established between attribute implication reasoning in FCACOI and inference in the logic LCOI+PLCOI, it indicate that formally proven inference rules (theorems) in LCOI+PLCOI are valid in the attribute implication reasoning of FCACOI, LCOI+PLCOI provides a logical foundation for attribute implication reasoning in FCACOI. To illustrate the capability of attribute implication reasoning in FCACOI, we discuss its application in a concrete example. Moreover, we explore attribute reduction of the formal context in FCACOI, propose two research frameworks for attribute reduction from different perspectives, and compare their characteristics.We believe that, based on richer logic and semantics, FCACOI elevates FCA from a theory that describes affirmations to one that can describe affirmations and its contradiction(either this or that), opposition(extreme negation) and intermediary (transitional states between oppositions).

Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model's answer. Existing faithfulness tests often place explicit bias cues in the user message, while agents may encounter preferences through tool returns or raw artifacts. We introduce FACE-Eval (Faithful Attribution of Cue Effects Evaluation), a 5,100-sample evaluation that varies cue location (user message or tool return) and explicitness (direct summary or raw artifact). We measure verbalized commitment among cue-following answers and unverbalized adoption among all cued samples. We evaluate 15 open-weight models from eight families, with total parameters ranging from 4B to 1.60T. Every model has lower verbalized commitment for tool-return than user-message cues and for implicit than explicit cues. Unverbalized adoption is higher for tool-return cues on all 15 models and for implicit cues in 28 of 30 model-channel comparisons. A source-attribution prompt narrows the channel gap on seven models, sometimes by increasing user-channel unverbalized adoption, while telling models that their reasoning will be monitored does not reliably close the gap. We also use two transcript monitors (GPT-5.6-Luna and GPT-4o-mini) to detect preference adoption in the largest model of each family. Across 32 model-channel-explicitness cells, higher unverbalized adoption is associated with lower detection ability for both monitors (Pearson r=-0.54 and r=-0.78, respectively). These results suggest that CoT monitoring may be less reliable when preference information arrives through tools or must be inferred from raw artifacts, within the single-call, prefilled-tool setting tested here.

Applications such as personalized assistance and proprietary document analysis require large language models (LLMs) to generate outputs from private data. Yet powerful LLMs typically cannot be deployed on the resource-constrained devices where private data resides, and uploading private data to cloud-hosted LLMs exposes sensitive information. Recent work addresses this tension with a cloud-edge collaborative decoding paradigm, where private data are kept on the edge with a small language model (SLM) producing next-token distributions, which are fused with predictions from a cloud LLM operating solely on public data. In this paper, we systematically analyze the privacy risks of such a paradigm with a novel evaluation framework using constructed QA datasets, which show that such collaboration can expose substantial private-context information. To address such privacy leakage, we propose CoVeil, a defense mechanism which dynamically optimizes transmitted signals to suppress leakage during decoding time while preserving the collaborative quality. Extensive evaluations demonstrate that CoVeil consistently improves the privacy-utility trade-off over existing baselines by reducing data leakage by up to 87.2%, with minimal accuracy loss.

As several mathematical conjectures have recently been settled using large language models (LLMs), the mathematical community has formulated norms and recommendations regarding the publishing of such results. These norms do not cover the disclosure of the prompts and precise software setup used to obtain those results, nor do they require that results be formalized in a manner that allows for machine verification. I argue that both of these are essential. In addition, since LLM-obtained results may be hard to understand, human authors have the responsibility to invent intuitive explanations.

Chain-of-thought (CoT) reasoning traces are increasingly proposed as a mechanism for AI oversight: a monitor inspecting a model's reasoning can, in principle, detect misbehavior invisible from outputs alone. This assumes CoT surfaces what a model is instructed to do regardless of the instructions given. We test this assumption along two axes. First, we introduce the Instruction-Compliance Gap (ICG): the difference in probability that a model's CoT explicitly references a hidden system prompt directive when that directive is malign versus benign. Across 100 task pairs and 8 frontier reasoning models from 5 families, we find consistent asymmetric disclosure, a higher probability of leaking malign hidden instructions than benign ones, in Qwen3-14B (Wilcoxon $p=0.0001$, $+13.9$pp), Qwen3-32B ($p=0.0011$, $+13.0$pp), Qwen3-235B ($p=0.035$, $+5.8$pp), and similar results with MiniMax-M2.5 and DeepSeek-R1. The detector has 100% precision against two independent blinded labelling passes, and an LLM monitor reading only the reasoning trace reproduces the asymmetry in all 8 models against directive-free controls, identifying the specific directive in 82% of malign traces which the detector classifies as clean. Second, steering vectors extracted in MiniMax-M2.5 via Contrastive Activation Addition causally induce hiding from bare prompts and suppress it from prompts that would otherwise produce it, replicating in Qwen3-14B under a pre-registered design. Benign and malign-derived hiding vectors are highly similar (cosine $0.804$ in MiniMax-M2.5; $0.970$ in Qwen3-14B), implying that in these models the disclosure asymmetry arises from differential activation of a shared hiding direction rather than separate mechanisms.

A wide range of methods have been proposed for interpreting language models, delivering important insights into their inner workings. However, different methods and their resulting insights stand in relative isolation: what could the underlying structure of language models be, such that they give rise to all our interpretations? In this work, we propose using Tensor Product Representations (TPRs) as a unifying hypothesis. TPRs give a concrete proposal for how compositional structure could be represented in vector space --- as filler-role bindings. We show, both mathematically and empirically, that TPRs can unify several prior interpretability methods: additive analogies, linear probing, sparse autoencoders, and activation patching. Mathematically, we show that these methods can all be derived from TPRs. Empirically, we apply the derivations to a range of different models --- from small toy models to LLMs --- to construct instances of each of the above interpretability methods; these constructed variants perform comparably to their standard variants. We view this work as a step toward what interpretability will ideally provide: a unified account of the nature of neural networks, corroborated not just by individual observations but also by an explanation of the connections between them.

Omni-modal large language models are increasingly evaluated on clean text--vision--audio inputs, where every channel is present, synchronized, and readily interpretable. Such scores are often taken as evidence of robust cross-modal fusion, but clean evaluation cannot tell whether success depends on stable cross-modal structure or on cues sufficient only in intact inputs. To address this gap, we define a modality fault line: a boundary at which model behavior becomes unstable when a modality remains present and human-interpretable, but its internal evidence structure is perturbed. We introduce SCEval (Structure-Corruption Evaluation) a diagnostic evaluation protocol that keeps the question, answer space, and modality channels fixed while applying controlled structural corruptions to text, vision, and audio individually and jointly. Built from $273$ human-verified tri-modal examples from Social-IQ, OmniBench, and VALOR, SCEval evaluates $15$ proprietary and open-source omni-modal systems. The results show that structural corruption lowers clean accuracy, text--vision damage forms the most stable shared fault line, and multi-modal degradation is non-additive rather than a simple function of the number of corrupted modalities. Clean omni-modal accuracy therefore does not establish that a model will remain reliable when cross-modal evidence becomes structurally unreliable.

As Large Language Models (LLMs) increasingly encourage users to disclose personal profiles for tailored assistance, measuring their political alignment becomes increasingly important. However, many existing benchmarks for assessing political behavior rely on closed-ended questions and do not fully capture how a model's stance may adapt to user-provided context during interaction. We introduce a framework that disentangles two distinct triggers of political sycophancy: opinion (aligning with explicit narratives) and identity (stereotyping based on demographic labels). Using 450 manually-checked political dilemmas as controlled probes, we evaluate 13 instruction-tuned LLMs. We uncover a dissociation: a model's susceptibility to explicit opinions does not necessarily predict its susceptibility to identity cues, and vice versa. When both signals are present, their effects are generally sub-additive rather than simply additive. Additionally, system-level personas primarily shift a model's baseline stance while having limited effect on the stance shift caused by user opinion or identity. Ultimately, our results suggest that LLM political stance is interactively and steerably vulnerable rather than being a fixed trait, highlighting how personalization may amplify identity- or opinion-conditioned shifts in the model's behaviors.

The online culinary ecosystem is increasingly populated by recipe content generated, modified, or summarized by Large Language Models (LLMs). While often plausible, such outputs may contain hallucinated ingredients, misrepresented quantities, or culturally implausible combinations, limiting their suitability for downstream applications and knowledge graph construction. In this paper, we present a semi-automated soundness assessment workflow for validating structured recipe data extracted and augmented by LLMs from informal culinary sources. Developed as part of FKG(.in), a knowledge graph of Indian food, the pipeline identifies and addresses common failure modes, including structural inconsistencies, semantic and logical incoherence, and deviations from the source text, through a multi-stage process combining formal grammars, vocabulary-based checks, statistical heuristics, Set Transformer-based coherence modeling, and retrieval-based verification. Although evaluated on Indian recipes, the proposed methods are applicable to broader multilingual and multicultural culinary domains. We provide a practical, auditable, and application-agnostic framework for validating LLM-augmented recipe data, thereby strengthening the foundations of machine-readable food knowledge infrastructures in the era of LLM-generated content.

Large language models deployed in specialized domains must improve in-domain performance without sacrificing general capabilities. Existing parameter-efficient fine-tuning methods are typically always on: their learned perturbations are applied to every input, which can degrade out-of-domain (OOD) performance. We propose Engram Adapter, a framework that repurposes pretraining-time conditional memory as a post-hoc adapter for frozen LLMs. It uses multi-channel matching over local n-gram patterns with explicit occupancy tracking as a lightweight selectivity prior, making residual injection more likely on in-domain inputs while a learned scalar gate suppresses incoherent OOD retrievals. We evaluate on Qwen3-4B and Qwen3-8B with AG-News and MedMCQA as adaptation tasks and OOD benchmarks spanning reasoning, translation, code generation, and legal reasoning. Engram Adapter improves in-domain accuracy while preserving 99.4%--100.1% of average OOD performance; on LegalBench it slightly exceeds the frozen base model on average, whereas comparable always-on baselines degrade sharply. Mechanistic analyses show that although OOD activations are non-zero, gate and projection attenuation reduce residuals to approximately 0.08% of hidden-state norm, yielding small KL drift and negligible accuracy change. These results suggest conditional activation is a promising route toward modular, retention-preserving domain specialization over frozen backbones.

Operators remain essential to Remotely Operated Vehicle (ROV) operation, yet often suffer from low situational awareness and high workload, both of which negatively affect safety. This paper presents a cognitive architecture consisting of an ontology and multiple Large Language Models (LLMs) to assist the operator at all stages of the mission. Each LLM is grounded with domain-specific information from the ontology and given a simple role to create a system that can support the operator at all stages of an operation. We are aiming to prove that using the two together will allow decisions to be grounded in the relevant domain knowledge, but also benefit from the reasoning capabilities of the LLM. Our framework determines if a mission is possible for a given Unmanned Underwater Vehicle (UUV), performs mission planning, and executes a given mission in simulation. The operator can be involved in planning and execution, ensuring the resulting plan is valid and that the vehicle behaves safely during execution. We compare different LLMs, Llama3, GPT-OSS, and Qwen2.5, to determine which are best suited to the different roles within our framework. We find that GPT-OSS performs best for feasibility assessment, planning, and execution, while Qwen2.5 is best suited to identifying mission types from natural language input.