arXiv：cs.CL· Zhihan Lei, Jiarui Yan, Joshua Momo, William W. Cohen·· 4 小时前
ARISE：从成功经验中学习可复用的 agent 子程序
Learning Reusable Agent Subroutines from Experience
AI 导读
ARISE（Agent Routine Induction from Successful Experience）从 agent trace 中识别反复出现的流程，并将其合成为可复用的 agent 子程序库。
正文
Abstract:Existing methods induce various forms of knowledge from agent traces, from sample workflows to programmatic skills. We propose ARISE (Agent Routine Induction from Successful Experience), which identifies recurring procedures in agent traces and synthesizes them into a reusable library of agent subroutines. Across five tasks in narrative deduction, rule application, and constraint planning, it is shown to be a more effective learning strategy than prompting methods and prose and code artifact induction methods. ARISE outperforms chain-of-thought in all ten model-task settings of the main evaluation. Compared to state-of-the-art methods in agent experience induction, our method scores 6.1 percentage points over the strongest evaluated baselines, and 11.5 percentage points over code-skill induction. In our controlled experiment, ARISE also improves average accuracy by up to 15.6 percentage points compared to formatting the induced knowledge as skills and by up to 19.1 points over rewriting it as code tools.
| Comments: | v2: major revision; method renamed to ARISE, new experiments, rewritten. 28 pages, 15 figures |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2606.02994 [cs.AI] |
| (or arXiv:2606.02994v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.02994 arXiv-issued DOI via DataCite |
Submission history
From: Zhihan Lei [view email]
[v1]
Tue, 2 Jun 2026 01:11:15 UTC (39 KB)
[v2]
Wed, 14 Oct 2026 02:22:53 UTC (747 KB)
来源：arXiv：cs.CL · arxiv.org