[2509.23735] Demystifying the Lifecycle of Failures in Platform-Orchestrated Agentic Workflows

Computer Science > Artificial Intelligence arXiv:2509.23735 (cs) [Submitted on 28 Sep 2025 (v1), last revised 27 Feb 2026 (this version, v2)] Title:Demystifying the Lifecycle of Failures in Platform-Orchestrated Agentic Workflows Authors:Xuyan Ma, Xiaofei Xie, Yawen Wang, Junjie Wang, Boyu Wu, Mingyang Li, Qing Wang View a PDF of the paper titled Demystifying the Lifecycle of Failures in Platform-Orchestrated Agentic Workflows, by Xuyan Ma and 6 other authors View PDF HTML (experimental) Abstract:Agentic workflows built on low-code orchestration platforms enable rapid development of multi-agent systems, but they also introduce new and poorly understood failure modes that hinder reliability and maintainability. Unlike traditional software systems, failures in agentic workflows often propagate across heterogeneous nodes through natural-language interactions, tool invocations, and dynamic control logic, making failure attribution and repair particularly challenging. In this paper, we present an empirical study of platform-orchestrated agentic workflows from a failure lifecycle perspective, with the goal of characterizing failure manifestations, identifying underlying root causes, and examining corresponding repair strategies. We present AgentFail, a dataset of 307 real-world failure cases collected from two representative agentic workflow platforms. Based on this dataset, we analyze failure patterns, root causes, and repair difficulty for various failure root causes and nodes...