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

Zhongwei Xie

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2NLP×1

Frequent co-authors

Yangqiu Song2×
Yuxuan Liu1×
Zhaochen Su1×
Lingyun Xie1×
Yuhao Zhang1×
Qing Zong1×

Research Timeline

2026
PatchWorld: Gradient-Free Optimization of Executable World Models

PatchWorld introduces a gradient-free framework to create executable Python world models from offline trajectories, achieving high planning scores by inducing symbolic belief-state programs.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

SkillRevise is an execution-grounded framework that iteratively refines initial, imperfect LLM agent skills by diagnosing defects from execution evidence and applying empirically validated edits, significantly boosting agent performance.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentMay 31, 2026

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

Yuxuan Liu, Zhaochen Su, Lingyun Xie, Yuhao Zhang +10 more

SkillRevise is an execution-grounded framework that iteratively refines initial, imperfect LLM agent skills by diagnosing defects from execution evidence and applying empirically validated edits, sign…

View →
cs.CLcs.AIRecentMay 29, 2026

PatchWorld: Gradient-Free Optimization of Executable World Models

Jiaxin Bai, Yue Guo, Yifei Dong, Jiaxuan Xiong +12 more

PatchWorld introduces a gradient-free framework to create executable Python world models from offline trajectories, achieving high planning scores by inducing symbolic belief-state programs.

View →