Xiaoyu Xu
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes Arbiter-K, a Governance-First execution architecture that treats LLMs as probabilistic units encapsulated by a deterministic kernel, significantly improving the security and reliability of agentic AI systems.
The paper identifies 'unintended long-term state poisoning'—a security risk where routine user interactions gradually corrupt an LLM agent's persistent state—and proposes a defense mechanism called StateGuard.
Papers
When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents
Xiaoyu Xu, Minxin Du, Qipeng Xie, Haobin Ke +2 more
The paper identifies 'unintended long-term state poisoning'—a security risk where routine user interactions gradually corrupt an LLM agent's persistent state—and proposes a defense mechanism called St…