# Demystifying the Lifecycle of Failures in Platform-Orchestrated Agentic Workflows

arXiv: https://arxiv.org/abs/2509.23735 · HTML: https://mlsanity.com/paper/2509.23735/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 17 of 17)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (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)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [AutoAgents: A Framework for Automatic Agent Generation](https://mlsanity.com/paper/2309.17288/) (2023)
- [AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?](https://mlsanity.com/paper/2509.03312/) (2025)
- [Small LLMs Are Weak Tool Learners: A Multi-LLM Agent](https://mlsanity.com/paper/2401.07324/) (2024)
- [Interactive Debugging and Steering of Multi-Agent AI Systems](https://mlsanity.com/paper/2503.02068/) (2025)
- [A Scalable Communication Protocol for Networks of Large Language Models](https://mlsanity.com/paper/2410.11905/) (2024)
- [Adaptive In-conversation Team Building for Language Model Agents](https://mlsanity.com/paper/2405.19425/) (2024)
- [Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks](https://mlsanity.com/paper/2508.13143/) (2025)
- [Aegis: Taxonomy and Optimizations for Overcoming Agent-Environment Failures in LLM Agents](https://mlsanity.com/paper/2508.19504/) (2025)
- [Improving Model Alignment Through Collective Intelligence of Open-Source LLMS](https://mlsanity.com/paper/2505.03059/) (2025)

## Built on by (most cited first, 10 of 10)

- [Are Tools All We Need? Unveiling the Tool-Use Tax in LLM Agents](https://mlsanity.com/paper/2605.00136/) (2026)
- [Efficient Failure Management for Multi-Agent Systems with Reasoning Trace Representation](https://mlsanity.com/paper/2603.21522/) (2026)
- [Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.14892/) (2026)
- [CUADebug: Diagnosing and Repairing Computer-Use Agent Failures](https://mlsanity.com/paper/2608.02643/) (2026)
- [Think Locally, Explain Globally: Graph-Guided LLM Investigations via Local Reasoning and Belief Propagation](https://mlsanity.com/paper/2601.17915/) (2026)
- [The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents](https://mlsanity.com/paper/2601.17344/) (2026)
- [Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents](https://mlsanity.com/paper/2605.21347/) (2026)
- [SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution](https://mlsanity.com/paper/2608.05573/) (2026)
- [Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inference](https://mlsanity.com/paper/2607.02882/) (2026)
- [Beyond LLM-Based Reasoning: Lightweight GNNs for Agent Failure Attribution](https://mlsanity.com/paper/2608.18575/) (2026)

## Abstract (arXiv)

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 in the workflow. Our findings reveal key failure mechanisms in agentic workflows and provide actionable guidelines for reliable failure repair, and real-world agentic workflow design.