Yu Hou

ClawKeeper is a comprehensive, multi-layered security framework designed to mitigate critical vulnerabilities in autonomous agent runtimes like OpenClaw by enforcing protection across skills, plugins, and system state.

PropGuard introduces a propagation-aware framework to safeguard LLM-MAS against malicious attacks by constructing a dual-view graph, identifying suspicious propagation paths, and applying source-guided remediation.

Evo-Attacker introduces a memory-augmented reinforcement learning framework to perform generalized, long-horizon tool attacks on LLM-MAS, significantly outperforming existing methods.

This study investigates human-AI collaboration in question answering, finding that while collaboration is beneficial, humans make suboptimal decisions by both under-relying on correct AI suggestions and over-relying when the AI is misleading.