资讯

TRACE-MAS: Diagnosing and Repairing Collaboration Failures in Multi-Agent Systems

📅 2026-11-19 ⏱️ 约 5 分钟阅读 ✍️ AI导航编辑部 🔗 arxiv.org
TRACE-MAS: Diagnosing and Repairing Collaboration Failures in Multi-Agent Systems
📝 内容摘要

Computer Science > Machine Learning [Submitted on 17 Nov 2026] Title:TRACE-MAS: Diagnosing and Repairing Collabora

📌 核心要点

  • Computer Science > Machine Learning
  • [Submitted on 17 Nov 2026]
  • Title:TRACE-MAS: Diagnosing and Repairing Collaboration Failures in Multi-Agent Systems

Computer Science > Machine Learning

[Submitted on 17 Nov 2026]

Title:TRACE-MAS: Diagnosing and Repairing Collaboration Failures in Multi-Agent Systems

View PDF HTML (experimental)Abstract:LLM-based multi-agent systems (MAS) rely on not only individual agent behaviors but also the interactions that connect agents, including message exchanges and task dependencies. Existing MAS safeguards mainly perform agent-level anomaly detection, which becomes insufficient when failures originate from agent interactions and detected anomalies do not necessarily reveal their true sources. To address this limitation, we propose \textbf{TRACE-MAS}, a finer-grained framework for diagnosing and repairing MAS failures. TRACE-MAS learns normal collaborative execution patterns from benign trajectories and detects deviations in agent state changes, message transitions, and task dependency evolutions. It further identifies responsible execution elements through source-aware attribution and selects minimal interventions to restore collaboration while preserving task-critical capabilities. Experiments on five MAS benchmarks demonstrate that TRACE-MAS significantly improves root-cause localization accuracy by \textbf{60.2}\% and achieves consistent gains in task recovery over strong MAS safeguards.

Additional Features

References & Citations

Loading...

Bibliographic and Citation Tools

Bibliographic Explorer (What is the Explorer?)

Connected Papers (What is Connected Papers?)

Litmaps (What is Litmaps?)

scite Smart Citations (What are Smart Citations?)

Code, Data and Media Associated with this Article

alphaXiv (What is alphaXiv?)

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub (What is DagsHub?)

Gotit.pub (What is GotitPub?)

Hugging Face (What is Huggingface?)

ScienceCast (What is ScienceCast?)

Demos

Recommenders and Search Tools

Influence Flower (What are Influence Flowers?)

CORE Recommender (What is CORE?)

IArxiv Recommender

(What is IArxiv?)

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.

来源arxiv.org· 本文为编辑整理,仅供参考