task · first seen 4 Oct 2026
LLM agent safety
Controlling tool-using language model agents to prevent harmful actions such as data leaks.
Mentions per week
PapersCodeDiscussion
Earliest sources
- G-CARB: Graph-Localized Conformal Agent Risk Budget for Compositional HarmPapers · 4 Oct 2026 · Zijun Yu, Yu Gu, Vahid Partovi Nia, Masoud Asgharian
- LatentRiskBench: Measuring State-Dependent Risks in Enterprise AgentsPapers · 13 Oct 2026 · Jingyue Cong, Estrid He, Zhuang Li, Nan Wu, Li Shen, Yameng Peng, Xinshu Li, And…
- AgentSafeEvo: Adversarial Co-Evolution for LLM Agent SafetyPapers · 14 Oct 2026 · Chenxu Wang, Xiaoyu Wen, Han Qi, Ziyuan Zhou, Cheng Jin, Chaochao Lu, Qiaosheng…
- Tail-risk-aware Agent Safety: Constraining Tail Risks Across Multi-step LLM Agent WorkflowsPapers · 7 Nov 2026 · Shilong Pan, Zhiliang Tian, Zihan Chen, Wentao Zou, Weiguo Chen, DongSheng Li
Latest sources
- Tail-risk-aware Agent Safety: Constraining Tail Risks Across Multi-step LLM Agent WorkflowsPapers · 7 Nov 2026 · Shilong Pan, Zhiliang Tian, Zihan Chen, Wentao Zou, Weiguo Chen, DongSheng Li
- AgentSafeEvo: Adversarial Co-Evolution for LLM Agent SafetyPapers · 14 Oct 2026 · Chenxu Wang, Xiaoyu Wen, Han Qi, Ziyuan Zhou, Cheng Jin, Chaochao Lu, Qiaosheng…
- LatentRiskBench: Measuring State-Dependent Risks in Enterprise AgentsPapers · 13 Oct 2026 · Jingyue Cong, Estrid He, Zhuang Li, Nan Wu, Li Shen, Yameng Peng, Xinshu Li, And…
- G-CARB: Graph-Localized Conformal Agent Risk Budget for Compositional HarmPapers · 4 Oct 2026 · Zijun Yu, Yu Gu, Vahid Partovi Nia, Masoud Asgharian