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

Suji Kim

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

ML×1AI×1NLP×1

Frequent co-authors

Kangsan Kim1×
Sung Ju Hwang1×

Research Timeline

2026
Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents

The paper introduces LearnWeak, an annotation-free framework that automatically specializes small computer-use agents by identifying and targeting their specific weaknesses using a stronger reference agent, achieving significant performance gains on OSWorld.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIcs.CLRecentMay 27, 2026

Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents

Suji Kim, Kangsan Kim, Sung Ju Hwang

The paper introduces LearnWeak, an annotation-free framework that automatically specializes small computer-use agents by identifying and targeting their specific weaknesses using a stronger reference…

View →