arXiv cs.AI· Bolin Shen, Yushun Dong·· 2 天前AI 评分31
ARIA：面向多智能体系统的运行时检查与修正框架
ARIA: Runtime Inspection and Amendment for Multi-Agent Systems
AI 导读
研究者提出 ARIA 框架，让紧凑模型学会在多智能体系统执行过程中判断何时干预、如何修正。团队从四个多智能体框架、六个基准、八种宿主模型收集超 24,000 条轨迹，构建了含 3,953 对执行验证修复的 ARIA 数据集，用于训练模型识别失败并给出修正方案。该模型在事后与运行时修复中均表现良好，并可泛化到未见过的框架和宿主模型，代码已开源。
正文 · 原文
Abstract:In LLM-based multi-agent systems (MAS), a local mistake can propagate as other agents build on it, turning a correctable error into a failed task. Diagnosing completed runs or repeatedly re-executing them to search for corrections does not provide a learned policy for intervening while execution is still in progress. We present Agent Runtime Inspection and Amendment (ARIA), a framework for learning when and how to repair ongoing multi-agent executions. Our key intuition is to turn execution-verified repairs into reusable supervision, moving repair search into data construction and training so that a learned model can intervene at runtime without repeatedly testing alternatives. First, we collect over 24{,}000 successful and failed trajectories across four multi-agent frameworks, six benchmarks, and eight host models. From these trajectories, we construct the ARIA dataset, to our knowledge the first large-scale dataset pairing failed multi-agent trajectories with execution-verified repairs. It contains 3{,}953 verified repair pairs, each specifying what went wrong, where to intervene, and how execution should continue. Then, we develop the ARIA framework for MAS-agnostic runtime inspection and amendment, designed to integrate with any MAS that exposes execution trajectories and supports continuation replacement. Using verified repairs as training examples, we teach a compact model to recognize when intervention is needed and how to correct an ongoing run. The aim is to learn repair strategies that apply to related failures in new configurations, rather than merely reproduce individual corrections. Finally, the trained ARIA model demonstrates strong repair performance in both post-hoc and runtime settings, with generalization to unseen frameworks and host models. Our code is available at this https URL.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.20780 [cs.AI] |
| (or arXiv:2610.20780v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20780 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Bolin Shen [view email]
[v1]
Wed, 14 Oct 2026 18:27:47 UTC (391 KB)
来源：arXiv cs.AI · arxiv.org