Skip to content
English

Switch theme

arXiv 2610.17860 · cs.AI · 2026-10-13

Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills

Letian Zhu, Han Li, Yifan Yao, Xinping Lei, Xinyu Che, Jiahao Wang, Dianyi Wang, Yucheng Fu and 4 more

NJU-LINK Lab

In latest · #303 Added on 2026-10-24

One-line takeaway

NJU-LINK's Socratic Skill Learning interleaves expert teaching with student practice — the student agent alone operates the environment and authors the Skill, questioning and testing advice — and introduces SkillTransferBench (35 task families, 408 executable cases) to test Skill reuse in fresh solver sessions.

南京大学 NJU-LINK 提出苏格拉底式技能学习:导师引导探索,学生智能体自己操作环境、写技能文件,可以质疑和测试建议;并构建 SkillTransferBench(35 个任务族、408 个可执行用例),在全新会话里检验技能能否迁移复用。

49HF upvotes
2GitHub stars
0Citations (Semantic Scholar)
43.5Buzz score

Read on arXiv PDF Hugging Face discussion Code

About this data

Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-26.

The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.

Data updated: Latest AI papers(UTC+8)