Chenxu Wang

LLM agents complete tasks through multi-turn tool calls, but malicious content in user queries, tool descriptions, or environment observations can steer them into unsafe actions. AgentSafeEvo frames safety as an attacker-defender game spanning diverse tasks and attack types: the attacker learns to build tasks that expose weaknesses in the defender's tool use, while the defender learns to complete tasks safely under those attacks, with learnability-guided task weighting adjusting each task's contribution to both updates. On agent safety and general capability benchmarks, the method improves adversarial robustness while maintaining general agent capabilities.

LLM agents complete tasks through multi-turn tool calls, but malicious content in user queries, tool descriptions, or environment observations can steer them into unsafe actions. AgentSafeEvo frames safety as an attacker-defender game spanning diverse tasks and attack types: the attacker learns to build tasks that expose weaknesses in the defender's tool use, while the defender learns to complete tasks safely under those attacks, with learnability-guided task weighting adjusting each task's contribution to both updates. On agent safety and general capability benchmarks, the method improves adversarial robustness while maintaining general agent capabilities.