From Evidence to Action: How Tool-Using Agents Fail

cs.CL, cs.AI

Submitted: 2026-10-06

Updated: 2026-10-06

Comments: 36 pages. Project page: https://safeact.github.io

Project page: https://safeact.github.io

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
• Coding Agents Don't Know When to Act
• Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?
• AgentAbstain: Do LLM Agents Know When Not to Act?
• Agentic Abstention: Do Agents Know When to Stop Instead of Act?
• When Agents Overtrust Environmental Evidence: An Extensible Agentic Framework for Benchmarking Evidence-Grounding Defects in LLM Agents
• HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?
• Agent-SafetyBench: Evaluating the Safety of LLM Agents

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering