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

Zichen Ding

3 indexed papers

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

Publications per year

3
26

Top categories

NLP×3AI×1HCI×1

Frequent co-authors

Jianxiang Yu2×
Jiapeng Zhu2×
Bochen Lin2×
Qier Cui2×
Xiang Li2×
Yikun Fu1×

Research Timeline

2026
Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents

The paper introduces MASA, a model-aware skill alignment framework that adaptively rewrites general and task-specific skills for LLM agents, achieving superior performance across diverse backbones and environments.

Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents

The paper introduces MASA, a model-aware skill alignment framework that adaptively rewrites general and task-specific skills for LLM agents, achieving superior performance across diverse backbones and environments.

MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop

The paper presents MacAgentBench, a comprehensive macOS agent benchmark for evaluating computer use agents.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.CLcs.HCEmpiricalRecentJun 21, 2026

MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop

Yikun Fu, Bowen Fu, Zhenyu Wu, Shuang Cheng +9 more

The paper presents MacAgentBench, a comprehensive macOS agent benchmark for evaluating computer use agents.

View →
cs.CLRecentMay 29, 2026

Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents

Jianxiang Yu, Jiapeng Zhu, Bochen Lin, Qier Cui +2 more

The paper introduces MASA, a model-aware skill alignment framework that adaptively rewrites general and task-specific skills for LLM agents, achieving superior performance across diverse backbones and…

View →
cs.CLRecentMay 29, 2026

Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents

Jianxiang Yu, Jiapeng Zhu, Bochen Lin, Qier Cui +2 more

The paper introduces MASA, a model-aware skill alignment framework that adaptively rewrites general and task-specific skills for LLM agents, achieving superior performance across diverse backbones and…

View →