Xuan Chen
5 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces SafeAudit, a meta-audit framework that systematically enumerates test cases and uses a quantitative metric to uncover significant residual unsafe behaviors in LLM agents that existing benchmarks miss.
This paper introduces the concept of Safety Geometry Collapse, demonstrating that multimodal inputs degrade the safety separation of LLMs, and proposes ReGap, a training-free method that adaptively corrects this drift to improve MLLM safety.
The paper introduces WIRE, a pipeline for diagnosing live intra-policy rule conflicts in LLM agents by identifying and testing specific rule pairs within a single prompt policy that can co-govern a realistic state.
The paper proposes a memory-augmented, traversability-aware framework for outdoor VLN that maintains stable, goal-consistent guidance even when semantic cues are interrupted or unavailable.
The JAMEL framework addresses the challenge of effective exploration in open-ended environments by jointly training agent memory and exploration policies using natural, novelty-driven signals.
Papers
Joint Agent Memory and Exploration Learning via Novelty Signals
Shizuo Tian, Xiaohong Weng, Rui Kong, Yuxuan Chen +8 more
The JAMEL framework addresses the challenge of effective exploration in open-ended environments by jointly training agent memory and exploration policies using natural, novelty-driven signals.