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。
Read on arXiv PDF Hugging Face discussion Code
Topics & disciplines
More on Agents
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲388
- Player-1: Learning to Play from Synthetic Experience ▲347
More on LLMs
- Jeva: System One Models from First Principles 2026-10-13 · ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions 2026-09-24 · ▲273
- WeVisOne-VL: Unified Visual Perception from Objects to Pixels 2026-10-22 · ▲247
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- OmniEdu: Open Foundation Models for Learning and Teaching 2026-09-19 · ▲240
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.