arXiv cs.CL· Yuan Xiong, Ziqi Miao, Qian Chen, Lijun Li, Ken Deng, Yequan Wang, Shizhu He, Jun Zhao, Kang Liu·· 12 小时前AI 评分33
SkillPyramid：面向自进化智能体的分层技能整合框架
SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents
AI 导读
SkillPyramid 是一个分层技能整合框架，通过复用已有技能经验并引入自进化机制，让智能体在执行任务中组合、验证和纳入新技能。在 ALFWorld、WebShop 和 ScienceWorld 上对四个骨干模型的实验显示，平均奖励提升 38.0%，执行步数减少 27.7%。该方法将技能集合从静态资源池转变为动态演化系统。
正文 · 原文
Abstract:Recent AI agents can flexibly invoke skills to solve complex tasks, but their long-term improvement is fundamentally constrained by a lack of systematic skill construction, accumulation, and transfer. In particular, without a unified framework for skill consolidation, agents tend to redundantly construct similar capabilities across different tasks, are unable to effectively transform experience into reusable assets, and struggle to generalize task-specific skills to novel scenarios. To address this limitation, we propose SkillPyramid, a skill consolidation framework that reuses existing skill experience for broader task generalization. Operating on a hierarchical skill topology, SkillPyramid further introduces a self-evolution mechanism that enables agents to compose, validate, and incorporate new skills during task execution. Experiments on ALFWorld, WebShop, and ScienceWorld across four backbone models show that SkillPyramid substantially increases the average reward by 38.0% and reduces execution steps by 27.7%. Overall, our method transforms a skill collection from a static resource pool into a dynamic evolution system.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2606.03692 [cs.AI] |
| (or arXiv:2606.03692v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.03692 arXiv-issued DOI via DataCite |
Submission history
From: Yuan Xiong [view email]
[v1]
Tue, 2 Jun 2026 14:14:27 UTC (1,344 KB)
[v2]
Fri, 23 Oct 2026 03:43:32 UTC (1,371 KB)
来源：arXiv cs.CL · arxiv.org