Saved in:
Bibliographic Details
Main Authors: West, Alva, Weng, Yixuan, Zhu, Minjun, Lin, Zhen, Ning, Zhiyuan, Zhang, Yue
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.10401
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908554150019072
author West, Alva
Weng, Yixuan
Zhu, Minjun
Lin, Zhen
Ning, Zhiyuan
Zhang, Yue
author_facet West, Alva
Weng, Yixuan
Zhu, Minjun
Lin, Zhen
Ning, Zhiyuan
Zhang, Yue
contents Failure attribution in multi-agent systems -- pinpointing the exact step where a decisive error occurs -- is a critical yet unsolved challenge. Current methods treat this as a pattern recognition task over long conversation logs, leading to critically low step-level accuracy (below 17\%), which renders them impractical for debugging complex systems. Their core weakness is a fundamental inability to perform robust counterfactual reasoning: to determine if correcting a single action would have actually averted the task failure. To bridge this \emph{counterfactual inference gap}, we introduce Abduct-Act-Predict (A2P) Scaffolding, a novel agent framework that transforms failure attribution from pattern recognition into a structured causal inference task. A2P explicitly guides a large language model through a formal three-step reasoning process within a single inference pass: (1) Abduction, to infer the hidden root causes behind an agent's actions; (2) Action, to define a minimal corrective intervention; and (3) Prediction, to simulate the subsequent trajectory and verify if the intervention resolves the failure. This structured approach leverages the holistic context of the entire conversation while imposing a rigorous causal logic on the model's analysis. Our extensive experiments on the Who\&When benchmark demonstrate its efficacy. On the Algorithm-Generated dataset, A2P achieves 47.46\% step-level accuracy, a 2.85$\times$ improvement over the 16.67\% of the baseline. On the more complex Hand-Crafted dataset, it achieves 29.31\% step accuracy, a 2.43$\times$ improvement over the baseline's 12.07\%. By reframing the problem through a causal lens, A2P Scaffolding provides a robust, verifiable, and significantly more accurate solution for automated failure attribution. Ours code are released at https://github.com/ResearAI/A2P.
format Preprint
id arxiv_https___arxiv_org_abs_2509_10401
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Abduct, Act, Predict: Scaffolding Causal Inference for Automated Failure Attribution in Multi-Agent Systems
West, Alva
Weng, Yixuan
Zhu, Minjun
Lin, Zhen
Ning, Zhiyuan
Zhang, Yue
Artificial Intelligence
Computation and Language
Failure attribution in multi-agent systems -- pinpointing the exact step where a decisive error occurs -- is a critical yet unsolved challenge. Current methods treat this as a pattern recognition task over long conversation logs, leading to critically low step-level accuracy (below 17\%), which renders them impractical for debugging complex systems. Their core weakness is a fundamental inability to perform robust counterfactual reasoning: to determine if correcting a single action would have actually averted the task failure. To bridge this \emph{counterfactual inference gap}, we introduce Abduct-Act-Predict (A2P) Scaffolding, a novel agent framework that transforms failure attribution from pattern recognition into a structured causal inference task. A2P explicitly guides a large language model through a formal three-step reasoning process within a single inference pass: (1) Abduction, to infer the hidden root causes behind an agent's actions; (2) Action, to define a minimal corrective intervention; and (3) Prediction, to simulate the subsequent trajectory and verify if the intervention resolves the failure. This structured approach leverages the holistic context of the entire conversation while imposing a rigorous causal logic on the model's analysis. Our extensive experiments on the Who\&When benchmark demonstrate its efficacy. On the Algorithm-Generated dataset, A2P achieves 47.46\% step-level accuracy, a 2.85$\times$ improvement over the 16.67\% of the baseline. On the more complex Hand-Crafted dataset, it achieves 29.31\% step accuracy, a 2.43$\times$ improvement over the baseline's 12.07\%. By reframing the problem through a causal lens, A2P Scaffolding provides a robust, verifiable, and significantly more accurate solution for automated failure attribution. Ours code are released at https://github.com/ResearAI/A2P.
title Abduct, Act, Predict: Scaffolding Causal Inference for Automated Failure Attribution in Multi-Agent Systems
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2509.10401