Research

Paper

AI LLM February 25, 2026

An Empirical Study of Bugs in Modern LLM Agent Frameworks

Authors

Xinxue Zhu, Jiacong Wu, Xiaoyu Zhang, Tianlin Li, Yanzhou Mu, Juan Zhai, Chao Shen, Yang Liu

Abstract

LLM agents have been widely adopted in real-world applications, relying on agent frameworks for workflow execution and multi-agent coordination. As these systems scale, understanding bugs in the underlying agent frameworks becomes critical. However, existing work mainly focuses on agent-level failures, overlooking framework-level bugs. To address this gap, we conduct an empirical study of 998 bug reports from CrewAI and LangChain, constructing a taxonomy of 15 root causes and 7 observable symptoms across five agent lifecycle stages: 'Agent Initialization','Perception', 'Self-Action', 'Mutual Interaction' and 'Evolution'. Our findings show that agent framework bugs mainly arise from 'API misuse', 'API incompatibility', and 'Documentation Desync', largely concentrated in the 'Self-Action' stage. Symptoms typically appear as 'Functional Error', 'Crash', and 'Build Failure', reflecting disruptions to task progression and control flow.

Metadata

arXiv ID: 2602.21806
Provider: ARXIV
Primary Category: cs.SE
Published: 2026-02-25
Fetched: 2026-02-26 05:00

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.21806v1</id>\n    <title>An Empirical Study of Bugs in Modern LLM Agent Frameworks</title>\n    <updated>2026-02-25T11:34:17Z</updated>\n    <link href='https://arxiv.org/abs/2602.21806v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.21806v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>LLM agents have been widely adopted in real-world applications, relying on agent frameworks for workflow execution and multi-agent coordination. As these systems scale, understanding bugs in the underlying agent frameworks becomes critical. However, existing work mainly focuses on agent-level failures, overlooking framework-level bugs. To address this gap, we conduct an empirical study of 998 bug reports from CrewAI and LangChain, constructing a taxonomy of 15 root causes and 7 observable symptoms across five agent lifecycle stages: 'Agent Initialization','Perception', 'Self-Action', 'Mutual Interaction' and 'Evolution'. Our findings show that agent framework bugs mainly arise from 'API misuse', 'API incompatibility', and 'Documentation Desync', largely concentrated in the 'Self-Action' stage. Symptoms typically appear as 'Functional Error', 'Crash', and 'Build Failure', reflecting disruptions to task progression and control flow.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.SE'/>\n    <published>2026-02-25T11:34:17Z</published>\n    <arxiv:primary_category term='cs.SE'/>\n    <author>\n      <name>Xinxue Zhu</name>\n    </author>\n    <author>\n      <name>Jiacong Wu</name>\n    </author>\n    <author>\n      <name>Xiaoyu Zhang</name>\n    </author>\n    <author>\n      <name>Tianlin Li</name>\n    </author>\n    <author>\n      <name>Yanzhou Mu</name>\n    </author>\n    <author>\n      <name>Juan Zhai</name>\n    </author>\n    <author>\n      <name>Chao Shen</name>\n    </author>\n    <author>\n      <name>Yang Liu</name>\n    </author>\n  </entry>"
}