一作ACL 2026Poster· Natural Language Processing
S afe MCP : Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
Lichao Wang · ZhaoXing Ren · Tianzhuo Yang · Jiaming Ji · Chi Harold Liu · Yaodong Yang · Juntao Dai
摘要
As Large Language Model (LLM) agents increasingly leverage the Model Context Protocol (MCP) to operate in complex environments, the expansion of their action spaces offers agents unsafe capabilities and underscores the risk of power-seeking. While broad action space and greater environment influe...