Author

Zang Li

h-index 5 View on Semantic Scholar

We have 2 of 15 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

SkillMentor: LLM Agent Self-Evolution via Learning Blind-Spot Diagnosis

SkillMentor, which trains a Mentor policy via reinforcement learning to generate diagnostic tasks, identify recurrent failure modes, and curate them into reusable corrective skills, is proposed, suggesting that blind-spot diagnosis is a learnable capability, enabling self-evolution without updating executor weights or...

Xiaoyi Bao, Yuanzhen Xie, Yunzhi Tan et al. · arXiv.org · 1 citation

Jul 2026

ProgramTab: Boosting Table Reasoning of LLMs via Programmatic Paradigm

The ProgramTab framework is proposed, which guides LLMs employing in-context learning to perform tabular data preprocessing with Python code, as well as the momentous contents extraction with row and column extraction and SQL generation, demonstrating that the ProgramTab framework effectively deals with table-based rea...

Pei Guo, Enjie Liu, Yunzhi Tan et al. · arXiv.org · 0 citations