SafeCoEvo: Co-Evolving Safety Harnesses and Guards for LLM Agents at Test-Time
LLM agents deployed in real-world environments continually encounter new tasks and safety risks, while execution feedback typically becomes available only after each task is completed. However, existing self-evolving approaches commonly rely on multiple rounds of optimization over fixed and repeatedly accessible task d...
Yu Cheng, Yong-Kang Hu, Shuai-Jie Ma et al.
· 0 citations