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

Yunfei Ge

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×3NLP×3ML×2Software Eng.×1

Frequent co-authors

Han Li4×
Xinyu Che3×
Shihao Li3×
Hang Yan3×
Xinping Lei3×
Jiaheng Liu3×

Research Timeline

2026
MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?

The paper introduces MMG2Skill, a closed-loop framework that converts noisy, human-oriented web guides into editable, executable skills, significantly improving agent performance across diverse tasks.

MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?

The paper introduces MMG2Skill, a closed-loop framework that converts noisy, human-oriented web guides into editable, executable skills, significantly improving agent performance across diverse tasks.

GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions

This paper introduces GameLogicBench, a benchmark for evaluating the ability of coding agents to implement gameplay rules in game development.

Highlighted terms show continued research focus across papers

Papers

cs.SEcs.AIcs.CLEmpiricalRecentSep 18, 2026

GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions

Xinyu Che, Yunfei Ge, Shihao Li, Yanchen Liu +8 more

This paper introduces GameLogicBench, a benchmark for evaluating the ability of coding agents to implement gameplay rules in game development.

View →
cs.CLcs.AIcs.LGRecent
Jun 1, 2026

MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?

Xinyu Che, Junqi Xiong, Yunfei Ge, Xinping Lei +9 more

The paper introduces MMG2Skill, a closed-loop framework that converts noisy, human-oriented web guides into editable, executable skills, significantly improving agent performance across diverse tasks.

View →
cs.CLcs.AIcs.LGRecentJun 1, 2026

MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?

Xinyu Che, Junqi Xiong, Yunfei Ge, Xinping Lei +9 more

The paper introduces MMG2Skill, a closed-loop framework that converts noisy, human-oriented web guides into editable, executable skills, significantly improving agent performance across diverse tasks.

View →