Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Xuan Chen

Xuan Chen

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

AI×4Crypto×2Robotics×1Software Eng.×1

Frequent co-authors

Lu Yan2×
Xiangyu Zhang2×
Shizuo Tian1×
Xiaohong Weng1×
Rui Kong1×
Yuxuan Chen1×

Research Timeline

2026
Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety

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.

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction

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.

Diagnosing Live Within-Policy Instruction Conflicts in LLM Agents with Witnessed Resolution Profiles

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.

TARIC: Memory-Augmented Traversability-Aware Outdoor VLN under Interrupted Semantic Cues

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.

Joint Agent Memory and Exploration Learning via Novelty Signals

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.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentJun 1, 2026

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.

View →
cs.ROcs.AIRecentMay 29, 2026

TARIC: Memory-Augmented Traversability-Aware Outdoor VLN under Interrupted Semantic Cues

Tianle Zeng, Hanjing Ye, Jianwei Peng, Jingwen Yu +2 more

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.

View →
cs.AIRecentMay 27, 2026

Diagnosing Live Within-Policy Instruction Conflicts in LLM Agents with Witnessed Resolution Profiles

Lu Yan, Xuan Chen, Xiangyu Zhang

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 re…

View →
cs.AIcs.CRRecentMay 18, 2026

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction

Jiahe Guo, Xiangran Guo, Jiaxuan Chen, Weixiang Zhao +5 more

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 co…

View →
cs.SEcs.CRRecentMar 18, 2026

Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety

Xuan Chen, Lu Yan, Ruqi Zhang, Xiangyu Zhang

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 exis…

View →