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

Fangxin Shang

2 indexed papers

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

Publications per year

2
26

Top categories

AI×1Software Eng.×1NLP×1

Frequent co-authors

Yehui Yang1×
Yibin Zhao1×
Dingrui Yang1×
Yuqi Wang1×

Research Timeline

2026
Semantic Triplet Restoration: A Novel Protocol for Hierarchical Table Understanding in Large Language Models

The paper introduces Semantic Triplet Restoration (STR), a novel protocol that converts complex table structures into atomic semantic triplets, improving table question answering by providing explicit semantic context and reducing reliance on layout-dependent serializations.

Hypothesis-Driven Skill Optimization for LLM Agents

This paper proposes Hypothesis-Driven Skill Optimization (HDSO), a train-free framework for improving action-oriented LLM agents with external skills while preserving their frozen inference endpoints.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.SEEmpiricalRecentJun 21, 2026

Hypothesis-Driven Skill Optimization for LLM Agents

Fangxin Shang, Yehui Yang

This paper proposes Hypothesis-Driven Skill Optimization (HDSO), a train-free framework for improving action-oriented LLM agents with external skills while preserving their frozen inference endpoints.

View →
cs.CLRecentMay 29, 2026

Semantic Triplet Restoration: A Novel Protocol for Hierarchical Table Understanding in Large Language Models

Yibin Zhao, Fangxin Shang, Dingrui Yang, Yuqi Wang

The paper introduces Semantic Triplet Restoration (STR), a novel protocol that converts complex table structures into atomic semantic triplets, improving table question answering by providing explicit…

View →