Chenyang Lyu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1NLP×1
Frequent co-authors
Research Timeline
2026
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback
The paper introduces a new security benchmark and framework to defend LLM agents against 'cognitive poisoning,' where malicious tools build trust through benign feedback before executing a harmful final action.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.CLRecentMay 17, 2026
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback
Lecheng Yan, Ruizhe Li, Xicheng Han, Wenxi Li +4 more
The paper introduces a new security benchmark and framework to defend LLM agents against 'cognitive poisoning,' where malicious tools build trust through benign feedback before executing a harmful fin…
View →