Yu Gong
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
PlanGuard is a training-free defense framework that uses an isolated Planner and hierarchical verification to defend LLM agents against Indirect Prompt Injection by verifying the consistency of planned actions.
The paper introduces Contextual Belief Management (CBM) to address how LLMs should manage accumulating information over long interactions, showing that reinforcement learning significantly improves belief state accuracy.
Papers
When Should Models Change Their Minds? Contextual Belief Management in Large Language Models
Haoming Xu, Weihong Xu, Zongrui Li, Mengru Wang +5 more
The paper introduces Contextual Belief Management (CBM) to address how LLMs should manage accumulating information over long interactions, showing that reinforcement learning significantly improves be…