Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inference
2026-07-03 • Software Engineering
Software Engineering
AI summaryⓘ
The authors address the problem that workflows built using large language models (LLMs) can fail unpredictably due to complex dependencies and tool interactions. They introduce FlowFixer, a system that turns workflow runs into symbolic traces to understand where and why failures happen, then creates targeted fixes based on this diagnosis. Their approach includes filtering out unlikely repairs early to save time. Tests on popular platforms show FlowFixer fixes more failures and identifies causes more accurately than previous methods. Overall, the authors provide a method to better spot and fix problems in automated workflows using symbolic reasoning.
agentic workflowslarge language models (LLMs)symbolic inferenceworkflow diagnosisfailure attributionroot cause analysisrepair patchestemporal dependenciesexecutable behavioral specificationsdynamic verification
Authors
Xuyan Ma, Yawen Wang, Junjie Wang, Xiaofei Xie, Boyu Wu, Mingyang Li, Dandan Wang, Qing Wang
Abstract
Platform-orchestrated agentic workflows have become a popular paradigm for developing LLM-based applications. However, their reliability remains a major challenge due to the uncertainty of LLM outputs, complex inter-node dependencies, and heterogeneous tool interactions. Existing agentic workflow optimization and agent enhancement methods primarily rely on trajectory-level feedback. Without explicitly identifying the underlying failure root causes, their resulting repair plans are often insufficiently targeted. We propose FlowFixer, a diagnosis-driven automated repair framework for agentic workflows. FlowFixer first transforms workflow executions into unified symbolic traces and performs symbolic inference to derive executable behavioral specifications that capture node correctness, temporal dependencies, and causal relationships. Based on specification verification, it conducts failure attribution and root cause analysis, and then generates targeted repair patches. To reduce verification costs, FlowFixer further employs a multi-dimensional pre-execution assessment to filter infeasible repairs before dynamic verification. We evaluate FlowFixer on workflow failures collected from three popular development platforms: Dify, Coze and n8n. Results show that FlowFixer achieves a repair success rate of 71.3%, outperforming state-of-the-art baselines by 11.9% to 27.6%. It also improves failure attribution accuracy by 4.8% to 33.1% and root cause analysis accuracy by 15.3% to 38.8%. This work offers a new perspective on reliable diagnosis and repair of agentic workflows through symbolic modeling and inference.