Autonomous Repair for Multi-Agent Systems via Monte-Carlo Tree Search
Hanxiao Lu, Tianyi Zhang
- Digest date
- 2026-08-03
- Submitted
- 2026-07-31
- arXiv ID
- 2607.29055
Summary
MARS formulates multi-agent system repair as an MCTS process with diagnosis-guided expansion and taxonomy-augmented evaluation, using partial rollouts instead of full simulations to save tokens. The authors also release StateMAS, a 1,310-trajectory benchmark of replayable MAS failures across four architectures and four LLM backbones, on which MARS improves absolute repair success from 3.0% to 12.1% over baselines.
Abstract
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.