arXiv:2606.01845v1 Announce Type: cross Abstract: Although large language models (LLMs) have shown considerable progress in pragmatic language understanding, prior research has focused mainly on their comprehension of verbal behavior. Nonetheless, non-verbal behavior remains a fundamental component of human communication, especially when deliberately utilized in isolation to convey indirect meanings. In this work, we present the […]
Monitoring Agentic Systems Before They’re Reliable
arXiv:2606.02494v1 Announce Type: cross Abstract: Agentic systems entering production typically operate as partially integrated assemblies where structural defects, not task-level errors, dominate the failure landscape. At this maturity level, task-level error detection may be infeasible: structural failure modes mask the signal that task-level monitors are designed to detect.We present a monitoring and triage methodology that […]
FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning
arXiv:2604.03893v2 Announce Type: replace Abstract: Current multimodal benchmarks for scientific reasoning primarily evaluate local information extraction — models recognize symbols and values and then perform textual inference. They do not assess whether models can reason over the global structural properties of formal diagrams, such as topology, conservation constraints, and the consistent mapping between visual patterns […]
Efficient LLM Moderation with Multi-Layer Latent Prototypes
arXiv:2502.16174v4 Announce Type: replace-cross Abstract: Although modern LLMs are aligned with human values during post-training, robust moderation remains essential to prevent harmful outputs at deployment time. Existing approaches suffer from performance-efficiency trade-offs and are difficult to customize to user-specific requirements. Motivated by this gap, we introduce Multi-Layer Prototype Moderator (MLPM), a lightweight and highly customizable […]
Understanding the Effects of Distractors on Reasoning Vision-Language Models
arXiv:2511.21397v2 Announce Type: replace-cross Abstract: How does irrelevant information (i.e., distractors) affect test-time scaling in vision-language models (VLMs)? Prior work on text-only language models has shown that textual distractors can intensify inverse scaling, causing models to reason longer but less effective reasoning traces. In this work, we investigate whether similar phenomena arise in multimodal settings. […]
“Do Not Mention This to the User”: Detecting and Understanding Malicious Agent Skills
arXiv:2602.06547v3 Announce Type: replace-cross Abstract: LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scripts that execute with full user privileges. Community registries have emerged to distribute these skills, but the security implications remain unstudied due to the absence of labeled threat data. This paper presents a […]
Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference
arXiv:2603.29002v3 Announce Type: replace-cross Abstract: Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to support complex reasoning. We show that these optimizations can be unified into a four-step memory processing pipeline: Prepare Memory, Compute Relevancy, Retrieval, and Apply to […]
Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning
arXiv:2605.26684v2 Announce Type: replace-cross Abstract: Group-based reinforcement learning (RL) methods have achieved remarkable success in improving the performance of large language models (LLMs) and have been rapidly extended to agentic tasks. However, their credit assignment relies heavily on coarse-grained trajectory-level attribution according to final outcomes, making it difficult to capture the contribution of individual steps, […]
THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models
arXiv:2606.01738v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to LLMs by exploiting conversational dynamics such as gradual escalation and cross-turn coordination. Existing defenses either rely on costly retraining — often degrading model utility — or apply single-turn analysis independently at each turn, failing to capture how risk accumulates along interaction trajectories. […]
Ranking vs. Assignment: The Metric Mismatch in Multi-View Object Association
arXiv:2606.02022v1 Announce Type: cross Abstract: Multi-view object association is an important computer vision problem that underlies many multi-camera perception tasks. While this task is naturally formulated as a constrained one-to-one matching problem, recent works heavily rely on pairwise ranking metrics like AP and FPR-95 for model evaluation. We highlight a fundamental mismatch between these metrics […]
FOAM: Frequency and Operator Error-Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo
arXiv:2606.02365v1 Announce Type: cross Abstract: Shampoo is attracting considerable attention for its superior performance on large-scale optimization benchmarks; yet it faces a significant practical bottleneck: the prohibitive computational overhead of matrix inversion. To mitigate this, practitioners typically rely on stale preconditioner updates, creating a fundamental trade-off between computational efficiency and optimization fidelity. In this work, […]
ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Emergent Adaptation
arXiv:2602.07883v3 Announce Type: replace Abstract: LLM-powered agentic systems excel at complex long-horizon tasks, but remain constrained by static configurations fixed before execution. Such rigidity forces a trade-off between domain-specific performance and cross-task generalization: strong priors and compact tool spaces aid specialization but weaken transfer, while task-agnostic workflows and broad action spaces expand coverage but dilute […]