works on
agent self-evolution 1blind-spot diagnosis 1in-context learning 1large language models 1LLM agents 1programmatic preprocessing 1python code generation 1reinforcement learning 1skill acquisition 1table reasoning 1text-to-sql 1

From the 2 of 9 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

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

Xiaoyi Bao, Yuanzhen Xie, Yunzhi Tan +5

The paper presents SkillMentor, a reinforcement‑learning trained mentor that enables large language model agents to learn how to identify and diagnose their own blind‑spot failures…