{"slug": "trace-mas-diagnosing-and-repairing-collaboration-failures-in-multi-agent-systems", "title": "TRACE-MAS: Diagnosing and Repairing Collaboration Failures in Multi-Agent Systems", "summary": "A new arXiv paper (2611.23362v1) introduces TRACE-MAS, a framework that learns normal collaborative execution patterns from benign trajectories to detect deviations in agent state changes, message transitions and task dependency evolutions in LLM-based multi-agent systems. TRACE-MAS uses source-aware attribution to identify responsible execution elements and selects minimal interventions to restore collaboration, improving root-cause localization accuracy by 60.2% across five MAS benchmarks versus strong MAS safeguards, with consistent gains in task recovery. The work targets a gap the authors identify in existing safeguards, which perform agent-level anomaly detection that misses failures originating from agent interactions.", "body_md": "arXiv:2611.23362v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/trace-mas-diagnosing-and-repairing-collaboration-failures-in-multi-agent-systems", "canonical_source": "https://arxiv.org/abs/2611.23362", "published_at": "2026-11-19 05:00:00+00:00", "updated_at": "2026-11-19 05:12:58.713675+00:00", "lang": "en", "topics": ["ai-agents", "ai-safety", "large-language-models", "ai-research"], "entities": ["TRACE-MAS", "arXiv"], "also_reported_by": [], "takeaway": "TRACE-MAS learns normal multi-agent execution patterns from benign trajectories and flags deviations in agent state changes, message transitions and task dependency evolutions, improving root-cause localization accuracy by 60.2% across five MAS benchmarks.", "recommendation": {"advice": "Monitor inter-agent message transitions and task dependency evolution, not just individual agent outputs, to localize multi-agent failures; the source reports 60.2% better root-cause accuracy across five benchmarks.", "playbook": "agent-architecture", "playbook_url": "https://wpnews.pro/playbooks/agent-architecture"}, "alternates": {"html": "https://wpnews.pro/news/trace-mas-diagnosing-and-repairing-collaboration-failures-in-multi-agent-systems", "markdown": "https://wpnews.pro/news/trace-mas-diagnosing-and-repairing-collaboration-failures-in-multi-agent-systems.md", "text": "https://wpnews.pro/news/trace-mas-diagnosing-and-repairing-collaboration-failures-in-multi-agent-systems.txt", "jsonld": "https://wpnews.pro/news/trace-mas-diagnosing-and-repairing-collaboration-failures-in-multi-agent-systems.jsonld"}}