Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems

• URL: http://arxiv.org/abs/2608.25920v2
• Date: Sat, 29 Aug 2026 11:11:17 GMT
• Title: Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems
• Abstract summary: We introduce SymTrace, a controlled evaluation framework that records the MAS execution trajectory and establishes intervention anchors.<n>During replay, it effectively reconstructs the execution before the anchor using recorded logs and only regenerates the downstream trajectory.<n>Our findings reveal that existing unguided rerun methods are highly unreliable, exhibiting low failure reproduction and repair rates.
• Score: 15.825635807363499
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As large language model (LLM)-based multi-agent systems (MASs) are increasingly applied to long-horizon complex tasks, their reliability has emerged as the core bottleneck hindering their real-world deployment. Existing MAS debugging and repair methods typically rely on rerunning and resampling the entire execution trajectory. However, a fundamental question remains to be answered: do these methods causally repair MAS failures or merely stochastically repair by leveraging the randomness of LLM sampling? To evaluate the effectiveness of MAS repair methods, we introduce SymTrace, a controlled evaluation framework that records the MAS execution trajectory and establishes intervention anchors. During replay, it effectively reconstructs the execution before the anchor using recorded logs and only regenerates the downstream trajectory, thereby enabling the reliable reproduction of MAS failures. We further construct the dataset SymFail, comprising 536 human-annotated failure trajectories with graph-linked locations, categories, and trace evidence. Based on these foundations, we conduct a large-scale empirical study across three mainstream MAS frameworks. Our findings reveal that existing unguided rerun methods are highly unreliable, exhibiting low failure reproduction and repair rates (only 67.97% and 6.90%, respectively). Building upon these findings, we further explore the effectiveness of a symptom-driven intervention method, which successfully repairs 20.15% of the failed cases (a 191.89% improvement to state-of-the-art repair methods). This study aims to provide actionable insights for MAS debugging and repair research, paving the way for the robust deployment of multi-agent systems.

Related papers

• Autonomous Repair for Multi-Agent Systems via Monte-Carlo Tree Search [4.313916831146957]
  We propose a search-based framework that formulates MAS repair as a Monte Carlo Tree Search (MCTS) process.<n>We also introduce StateMAS, a large-scale MAS repair benchmark with 1,310 replayable multi-agent failure trajectories.
  arXiv  Detail & Related papers  (2026-07-31T06:18:48Z)
• PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents [62.36339598951133]
  We present PhoenixRepair, a multi-agent framework that explores multiple candidate edit locations and generates better patches.<n>PhoenixRepair achieves the largest relative improvement of 7.8% over SWE-agent under DeepSeek-V3.1, and attains the highest resolved rate of 76.0% Pass@1 under MiniMax-M2.5.
  arXiv  Detail & Related papers  (2026-07-21T08:49:30Z)
• Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents [80.03824805228719]
  A major challenge in developing computer-use agents is collecting large-scale, high-quality trajectories.<n>We propose a data-centric paradigm that turns failed trajectories into agent improvements.<n>We validate this approach with the state-of-the-art OpenCUA-72B model on the OSWorld benchmark.
  arXiv  Detail & Related papers  (2026-06-30T07:44:37Z)
• Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems [0.10210859604701106]
  Self-healing agentic orchestrator treats reliability as a runtime bounded control problem.<n>Self-healing achieves 98.8% task success, compared with 94.5% for retry-only and 93.8% for full replanning.
  arXiv  Detail & Related papers  (2026-05-31T19:27:22Z)
• Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis [68.28714988482703]
  Process Reward Models (PRMs) have achieved remarkable success in augmenting the reasoning capabilities of Large Language Models (LLMs)<n>We present a study revealing that general-domain PRMs struggle to supervise data analysis agents.<n>We introduce DataPRM, a novel environment-aware generative process reward model.
  arXiv  Detail & Related papers  (2026-04-27T09:00:30Z)
• TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code [11.207330722400764]
  We present TraceCoder, a framework that emulates the observe-analyze-repair process of human experts.<n>The framework first instruments the code with diagnostic probes to capture fine-grained runtime traces.<n>It then conducts causal analysis on these traces to accurately identify the root cause of the failure.
  arXiv  Detail & Related papers  (2026-02-06T16:59:48Z)
• DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems [48.971606069204825]
  DoVer is an intervention-driven debug framework for large language model (LLM)-based multi-agent systems.<n>It augments hypothesis generation with active verification through targeted interventions.<n>DoVer flips 18-28% of failed trials into successes, achieves up to 16% milestone progress, and validates or refutes 30-60% of failure hypotheses.
  arXiv  Detail & Related papers  (2025-12-07T09:23:48Z)
• Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction [58.51530390018909]
  Large Language Model based multi-agent systems excel at collaborative problem solving but remain brittle to cascading errors.<n>We present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction.
  arXiv  Detail & Related papers  (2025-10-16T05:35:37Z)
• Testing and Enhancing Multi-Agent Systems for Robust Code Generation [21.38351747327572]
  Multi-agent systems (MASs) have emerged as a promising paradigm for automated code generation.<n>Despite their prosperous development and adoption, their robustness remains pressingly under-explored.<n>This paper presents the first comprehensive study examining the robustness of MASs for code generation through a fuzzing-based testing approach.
  arXiv  Detail & Related papers  (2025-10-12T05:45:04Z)
• Why Do Multi-Agent LLM Systems Fail? [87.90075668488434]
  We introduce MAST-Data, a comprehensive dataset of 1600+ annotated traces collected across 7 popular MAS frameworks.<n>We build the first Multi-Agent System Failure taxonomy (MAST)<n>We leverage MAST and MAST-Data to analyze failure patterns across models (GPT4, Claude 3, Qwen2.5, CodeLlama) and tasks (coding, math, general agent)
  arXiv  Detail & Related papers  (2025-03-17T19:04:38Z)
• Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking [83.48804199140758]
  We propose a learning-to-mis-rank formulation to perturb the ranking of the system output. We also perform a back-box attack by developing a novel multi-stage network architecture. Our method can control the number of malicious pixels by using differentiable multi-shot sampling.
  arXiv  Detail & Related papers  (2020-04-08T18:48:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.