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

Lei Liang

3 indexed papers

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

Publications per year

3
26

Top categories

NLP×3AI×2ML×2Multiagent×2

Frequent co-authors

Chengtao Gan1×
Zhiqiang Liu1×
Long Jin1×
Yushan Zhu1×
Wen Zhang1×
Zhuoyun Yu1×

Research Timeline

2026
LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis

The paper introduces LongDS, a new benchmark for long-horizon, multi-turn data analysis, demonstrating that current AI agents struggle significantly with maintaining and updating complex analytical states over extended interactions.

SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories

SkillAdaptor is a novel, training-free framework that enables stable, step-level adaptation of external skills for LLM agents by precisely attributing failures to specific skills.

CRAFTQA: A Code-Driven Adaptive Framework for Complex Structured Data Reasoning

CRAFTQA introduces a novel adaptive, code-driven framework that significantly enhances complex structured data reasoning by dynamically generating custom code functions beyond predefined operations.

Highlighted terms show continued research focus across papers

Papers

cs.CLRecentJun 1, 2026

CRAFTQA: A Code-Driven Adaptive Framework for Complex Structured Data Reasoning

Chengtao Gan, Zhiqiang Liu, Long Jin, Yushan Zhu +2 more

CRAFTQA introduces a novel adaptive, code-driven framework that significantly enhances complex structured data reasoning by dynamically generating custom code functions beyond predefined operations.

View →
cs.CLcs.AIcs.LGRecentMay 31, 2026

SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories

Zhuoyun Yu, Xin Xie, Wuguannan Yao, Chenxi Wang +3 more

SkillAdaptor is a novel, training-free framework that enables stable, step-level adaptation of external skills for LLM agents by precisely attributing failures to specific skills.

View →
cs.LGcs.AIcs.CLRecentMay 28, 2026

LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis

Kewei Xu, Xiaoben Lu, Shuofei Qiao, Zihan Ding +3 more

The paper introduces LongDS, a new benchmark for long-horizon, multi-turn data analysis, demonstrating that current AI agents struggle significantly with maintaining and updating complex analytical st…

View →