基于强化学习的渐进式智能体技能生成

Computer Science > Machine Learning arXiv:2608.01678 (cs) [Submitted on 3 Aug 2026 (v1), last revised 10 Sep 2026 (this version, v2)] Title:Progressive Agent Skill Generation via Reinforcement Learning Authors:Junhao Shen, Zhanqiu Zhang, Yiwen Guo, Hong Cheng View a PDF of the paper titled Progressive Agent Skill Generation via Reinforcement Learning, by Junhao Shen and Zhanqiu Zhang and Yiwen Guo and Hong Cheng View PDF HTML (experimental) Abstract:Recent large language model agents often use external skills as modular procedural units that condition inference and improve complex task solving. Thus, automatically generating high-quality skills from documents or experience has become an important problem. Existing skill generation methods largely rely on heuristics or pipeline-style consolidation, which must be specially designed for different evidence sources. In contrast, learning-based approaches offer a more unified way to model skill generation across heterogeneous sources. However, learning-based skill generation remains challenging because skills lack a natural supervision signal based on relevance or correctness; their value can largely be determined only by whether they improve the behavior of the agent on downstream tasks. To address this challenge, we proposeSkill-$\alpha$, a reinforcement learning method that learns a unified policy for progressive skill generation. Specifically, we construct each skill by repeatedly applying the learned policy to successive source evidence and introduce a novel rollback reward that evaluates each edit by comparing downstream execution under the original and edited skills on an anchored query. Extensive experiments show thatSkill-$\alpha$ generates more effective skills than methods based on heuristics or pipelines in both document-to-skill and experience-to-skill settings. Under the main GPT-4o worker,Skill-$\alpha$ improves average downstream success rates over the strongest skill-generation baseline by 3.1 points on CL-Bench and 6.7 points on tau2-bench. Further ablations and analysis validate the importance of rollback reward and progressive generation. Comments: Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL) Cite as: arXiv:2608.01678 [cs.LG] (or arXiv:2608.01678v2 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.01678 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Junhao Shen [view email] [v1] Mon, 3 Aug 2026 04:14:59 UTC (254 KB) [v2] Thu, 10 Sep 2026 12:26:27 UTC (275 KB) Full-text links: Access Paper: View a PDF of the paper titled Progressive Agent Skill Generation via Reinforcement Learning, by Junhao Shen and Zhanqiu Zhang and Yiwen Guo and Hong Cheng View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG new | recent | 2026-08 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) IArxiv recommender toggle IArxiv Recommender (What is IArxiv?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)