# Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference

arXiv: https://arxiv.org/abs/2509.08682 · HTML: https://mlsanity.com/paper/2509.08682/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 38 references that are in the map.
- First posted on arXiv 10 Sep 2025.

## Builds on (most cited first, 27 of 27)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [GPTScore: Evaluate as You Desire](https://mlsanity.com/paper/2302.04166/) (2023)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges](https://mlsanity.com/paper/2406.12624/) (2024)
- [SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning](https://mlsanity.com/paper/2308.00436/) (2023)
- [A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness](https://mlsanity.com/paper/2411.03350/) (2024)
- [TRAIL: Trace Reasoning and Agentic Issue Localization](https://mlsanity.com/paper/2505.08638/) (2025)
- [Interactive Debugging and Steering of Multi-Agent AI Systems](https://mlsanity.com/paper/2503.02068/) (2025)
- [EcoAssistant: Using LLM Assistant More Affordably and Accurately](https://mlsanity.com/paper/2310.03046/) (2023)
- [Offline Training of Language Model Agents with Functions as Learnable Weights](https://mlsanity.com/paper/2402.11359/) (2024)
- [CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks](https://mlsanity.com/paper/2507.10535/) (2025)
- [Single-agent or Multi-agent Systems? Why Not Both?](https://mlsanity.com/paper/2505.18286/) (2025)
- [CF-GODE: Continuous-Time Causal Inference for Multi-Agent Dynamical Systems](https://mlsanity.com/paper/2306.11216/) (2023)
- [Towards Acyclic Preference Evaluation of Language Models via Multiple Evaluators](https://mlsanity.com/paper/2410.12869/) (2024)
- [EcoAct: Economic Agent Determines When to Register What Action](https://mlsanity.com/paper/2411.01643/) (2024)
- [Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning](https://mlsanity.com/paper/2412.15619/) (2024)

## Built on by (most cited first, 18 of 18)

- [DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems](https://mlsanity.com/paper/2512.06749/) (2025)
- [Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation](https://mlsanity.com/paper/2603.25001/) (2026)
- [AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces](https://mlsanity.com/paper/2608.23041/) (2026)
- [Agentic Services Computing](https://mlsanity.com/paper/2509.24380/) (2025)
- [Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.14892/) (2026)
- [StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems](https://mlsanity.com/paper/2606.03467/) (2026)
- [Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model](https://mlsanity.com/paper/2608.13867/) (2026)
- [EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems](https://mlsanity.com/paper/2609.01360/) (2026)
- [Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories](https://mlsanity.com/paper/2605.29893/) (2026)
- [LongRCA Bench: Root-Cause Localization in Long-Horizon Agent Trajectories](https://mlsanity.com/paper/2608.15242/) (2026)
- [trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories](https://mlsanity.com/paper/2609.00038/) (2026)
- [FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills](https://mlsanity.com/paper/2607.21596/) (2026)
- [Adaptive Influence Graphs for Failure Attribution in Multi-Agent Systems](https://mlsanity.com/paper/2608.24361/) (2026)
- [Detect Before You Attribute: Cascade Failure Attribution for Multi-Agent Systems](https://mlsanity.com/paper/2608.29646/) (2026)
- [Agent System Operations: Categorization, Challenges, and Future Directions](https://mlsanity.com/paper/2606.01581/) (2026)
- [World Models in Pieces: Structural Certification for General Agents](https://mlsanity.com/paper/2606.24842/) (2026)
- [AUDITA: certified auditing and causal attribution of adverse outcomes in autonomous multi-agent systems](https://mlsanity.com/paper/2608.22160/) (2026)
- [Causal Attribution for Agentic Decisions: Estimators, Coupling, and a Traceability Specification](https://mlsanity.com/paper/2609.06445/) (2026)

## Abstract (arXiv)

Multi-agent systems (MAS) are critical for automating complex tasks, yet their practical deployment is severely hampered by the challenge of failure attribution. Current diagnostic tools, which rely on statistical correlations, are fundamentally inadequate; on challenging benchmarks like Who&When, state-of-the-art methods achieve less than 15% accuracy in locating the root-cause step of a failure. To address this critical gap, we introduce the first failure attribution framework for MAS grounded in multi-granularity causal inference. Our approach makes two key technical contributions: (1) a performance causal inversion principle, which correctly models performance dependencies by reversing the data flow in execution logs, combined with Shapley values to accurately assign agent-level blame; (2) a novel causal discovery algorithm, CDC-MAS, that robustly identifies critical failure steps by tackling the non-stationary nature of MAS interaction data. The framework's attribution results directly fuel an automated optimization loop, generating targeted suggestions whose efficacy is validated via counterfactual simulations. Evaluations on the Who&When and TRAIL benchmarks demonstrate a significant leap in performance. Our method achieves up to 36.2% step-level accuracy. Crucially, the generated optimizations boost overall task success rates by an average of 22.4%. This work provides a principled and effective solution for debugging complex agent interactions, paving the way for more reliable and interpretable multi-agent systems.