T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search

ArXi:2603.22341v1 Announce Type: cross While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLMs), such approaches fail to capture agent-specific vulnerabilities that emerge through multi-step tool execution, particularly in rapidly growing ecosystems such as the Model Context Protocol (MCP). To address this gap, we propose a trajectory-aware evolutionary search method, T-MAP, which leverages execution trajectories to guide the discovery of adversarial prompts.