从失败中学习：面向小型语言模型工具使用代理的异构图记忆

Computer Science > Machine Learning arXiv:2609.28003 (cs) [Submitted on 23 Sep 2026] Title:Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents Authors:Jiaxing Li, Lei Song, Rui Dong, Youyong Kong View a PDF of the paper titled Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents, by Jiaxing Li and 3 other authors View PDF HTML (experimental) Abstract:Small and medium-sized language models offer cost-effective executors for tool-using agents, making them attractive for local and large-scale deployment. However, in long-horizon and stateful environments, they often make structural errors such as missing required observations, performing premature writes, repeating failed calls, and violating action preconditions. These errors can lead to incorrect state updates, policy violations, and costly or irreversible consequences, making reliable tool execution a critical deployment challenge. Existing fine-tuning approaches require substantial data and computation, while flat memory may retrieve failed actions without preserving their causal context or safety conditions. In this paper, we propose FRESH, a Failure-aware Retrieval framework over Experience-Structured Heterogeneous graphs, which transforms historical successes and failures into structured external experience for tool-using agents. By explicitly modeling the dependencies among tasks, actions, errors, repairs, and execution conditions, FRESH helps frozen language models reuse reliable strategies, avoid recurring failures, and make safer decisions in stateful tool interactions. Experiments on $\tau$-Bench and AppWorld with multiple open-source models show that FRESH consistently improves task success and tool-use reliability over no-memory agents and representative memory-based baselines. Subjects: Machine Learning (cs.LG) Cite as: arXiv:2609.28003 [cs.LG] (or arXiv:2609.28003v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2609.28003 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Jiaxing Li [view email] [v1] Wed, 23 Sep 2026 12:31:39 UTC (3,061 KB) Full-text links: Access Paper: View a PDF of the paper titled Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents, by Jiaxing Li and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG new | recent | 2026-09 Change to browse by: cs 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?)