{"slug": "autonomous-repair-for-multi-agent-systems-via-monte-carlo-tree-search", "title": "Autonomous Repair for Multi-Agent Systems via Monte-Carlo Tree Search", "summary": "Researchers propose MARS, a Monte Carlo Tree Search-based framework for automatically repairing multi-agent systems, and introduce StateMAS, a benchmark with 1,310 replayable failure trajectories. On StateMAS, MARS outperforms state-of-the-art methods by 3.0% to 12.1% absolute improvement across settings while maintaining comparable token consumption.", "body_md": "arXiv:2607.29055v1 Announce Type: new\nAbstract: Multi-agent systems (MAS) are increasingly deployed to solve complex tasks. In case of incorrect or unsatisfactory outputs, users have to manually locate agent mistakes by inspecting agent trajectories (i.e., {\\em failure attribution}) and provide feedback to refine the outputs (i.e., {\\em repair}). Despite some recent work in MAS failure attribution, automated mechanisms to recover from such mistakes remain largely unexplored. To bridge this gap, we propose MARS, a search-based framework that formulates MAS repair as a Monte Carlo Tree Search (MCTS) process and navigates the vast space of potential repairs via diagnosis-guided expansion with taxonomy-augmented evaluation. Unlike standard MCTS, which evaluates a complete simulation via full rollout, MARS evaluates the agent trajectory using partial rollout to reduce token consumption. Furthermore, we introduce StateMAS, a large-scale MAS repair benchmark with 1,310 replayable multi-agent failure trajectories spanning four types of agent architectures and four LLM backbones. Experiments on StateMAS demonstrate that MARS consistently outperforms state-of-the-art methods, achieving an absolute improvement from 3.0\\% to 12.1\\% across all settings, while maintaining a comparable token consumption cost. The ablation study further confirms that taxonomy-augmented evaluation and diagnosis-guided expansion are critical to achieving these performance gains.", "url": "https://wpnews.pro/news/autonomous-repair-for-multi-agent-systems-via-monte-carlo-tree-search", "canonical_source": "https://www.machinebrief.com/news/autonomous-repair-for-multi-agent-systems-via-monte-carlo-tr-bnsg", "published_at": "2026-08-03 04:00:00+00:00", "updated_at": "2026-08-03 04:34:58.716095+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-agents", "ai-research"], "entities": ["MARS", "StateMAS", "Monte Carlo Tree Search"], "alternates": {"html": "https://wpnews.pro/news/autonomous-repair-for-multi-agent-systems-via-monte-carlo-tree-search", "markdown": "https://wpnews.pro/news/autonomous-repair-for-multi-agent-systems-via-monte-carlo-tree-search.md", "text": "https://wpnews.pro/news/autonomous-repair-for-multi-agent-systems-via-monte-carlo-tree-search.txt", "jsonld": "https://wpnews.pro/news/autonomous-repair-for-multi-agent-systems-via-monte-carlo-tree-search.jsonld"}}