Tian Zhang

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.

This paper conducts the first real-world safety evaluation of the personal AI agent OpenClaw, demonstrating that its broad system access creates inherent vulnerabilities that significantly increase the attack success rate regardless of the underlying large language model.

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.

The paper introduces Autonomous Agentic Data Engineering, demonstrating that LLMs can autonomously plan and optimize end-to-end data curation pipelines, leading to substantial performance gains in specialized models.

The paper introduces the Insertion Process (IP), a novel stochastic generative model that learns variable-length, non-monotonic sequence generation by explicitly modeling the insertion order of tokens.

This paper investigates whether model compression techniques (like quantization and pruning) preserve a Large Language Model's ability to quantify its own uncertainty, finding that accuracy-only evaluation is insufficient for assessing deployment readiness.

This paper presents GRAIL, a digital generation pipeline that synthesizes human-object interactions for humanoid robots.