arXiv:2609.05721v1 Announce Type: new Abstract: Understanding whether language-model embeddings encode structured real-world information is important for…
Category: AI
CUSP: Decomposable Collective Uncertainty for Multi-Agent Multimodal Reasoning
arXiv:2609.05708v1 Announce Type: new Abstract: Aggregating heterogeneous vision-language models (VLMs) can improve multimodal reasoning, but neither an…
Beyond Prompts: Measuring and Optimizing LLM Tool-Agent Harnesses
arXiv:2609.05736v2 Announce Type: new Abstract: LLM tool agents can be improved without retraining by modifying the runtime harness around a fixed model:…
Agents Trust Tools Too Much: Measuring Reliance on Unreliable Tools
arXiv:2609.05587v1 Announce Type: new Abstract: Existing evaluations of tool-using agents primarily measure whether an agent can successfully complete…
EdgeMem: LLM-Free Agent Memory Construction and Retrieval via Evidence-Preserving Multi-Anchor Hypergraph
arXiv:2609.05553v1 Announce Type: new Abstract: Agent memory allows LLM agents to use earlier interactions when answering new queries. Existing methods…
Deep belief networks are exact
arXiv:2609.05572v1 Announce Type: new Abstract: We prove that every strictly positive probability distribution on \(\{-1,1\}^n\) is represented exactly by…
Planning and Scheduling Business Processes under Control-Flow Uncertainty
arXiv:2609.05578v1 Announce Type: new Abstract: Scheduling activities in business processes can improve efficiency (e.g., reduce makespan), but is…
Anthropic Discloses Fourth Cyber Incident in Alignment Assessment
Anthropic on September 9, 2026, published an alignment assessment of recent cybersecurity incidents, disclosing a fourth incident in which a Claude model…
EnvCraft: Synthesizing Executable Environments in Agentic RL for Claw-like Agent
arXiv:2609.05576v1 Announce Type: new Abstract: The paradigm of LLMs has rapidly shifted from passive language interfaces to autonomous Claw-like agents…
Reasoning-Aware Compression: Identifying and Protecting Vulnerable Reasoning Circuits for Energy-Efficient LLM Deployment
arXiv:2609.05512v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) impose substantial energy costs during deployment, yet current compression…