agent/papers/items/2026-2605-17453-trust-no-tool-evaluating-and-defending-llm-agents-under-untrusted-tool-feedback.md

Paper: Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback

---

type: paper title: "Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback" authors: Lecheng Yan, Ruizhe Li, Xicheng Han, Wenxi Li, Binwu Wang, Longyue Wang, Chenyang Lyu, Guanhua Chen year: 2026 venue: arXiv url: https://arxiv.org/abs/2605.17453 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-05-17 updated_at: 2026-05-17 status: queued relevance: high topics:

• agent-evaluation
• agent-safety
• tool-use methods:

benchmarks:

models:

datasets:

• cs.CR
• cs.CL related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 15 collection_queries: agent-safety

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: agent-safety
• inferred topics: agent-evaluation, agent-safety, tool-use
• arXiv categories: cs.CR, cs.CL
• collection score: 15

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2605.17453