Research

Paper

AI LLM March 06, 2026

XAI for Coding Agent Failures: Transforming Raw Execution Traces into Actionable Insights

Authors

Arun Joshi

Abstract

Large Language Model (LLM)-based coding agents show promise in automating software development tasks, yet they frequently fail in ways that are difficult for developers to understand and debug. While general-purpose LLMs like GPT can provide ad-hoc explanations of failures, raw execution traces remain challenging to interpret even for experienced developers. We present a systematic explainable AI (XAI) approach that transforms raw agent execution traces into structured, human-interpretable explanations. Our method consists of three key components: (1) a domain-specific failure taxonomy derived from analyzing real agent failures, (2) an automatic annotation system that classifies failures using defined annotation schema, (3) a hybrid explanation generator that produces visual execution flows, natural language explanations, and actionable recommendations. Through a user study with 20 participants (10 technical, 10 non-technical), we demonstrate that our approach enables users to identify failure root causes 2.8 times faster and propose correct fixes with 73% higher accuracy compared to raw execution traces. Importantly, our structured approach outperforms ad-hoc state of the art models explanations by providing consistent, domain-specific insights with integrated visualizations. Our work establishes a framework for systematic agent failure analysis, addressing the critical need for interpretable AI systems in software development workflows

Metadata

arXiv ID: 2603.05941
Provider: ARXIV
Primary Category: cs.SE
Published: 2026-03-06
Fetched: 2026-03-09 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.05941v1</id>\n    <title>XAI for Coding Agent Failures: Transforming Raw Execution Traces into Actionable Insights</title>\n    <updated>2026-03-06T06:18:20Z</updated>\n    <link href='https://arxiv.org/abs/2603.05941v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.05941v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Large Language Model (LLM)-based coding agents show promise in automating software development tasks, yet they frequently fail in ways that are difficult for developers to understand and debug. While general-purpose LLMs like GPT can provide ad-hoc explanations of failures, raw execution traces remain challenging to interpret even for experienced developers. We present a systematic explainable AI (XAI) approach that transforms raw agent execution traces into structured, human-interpretable explanations. Our method consists of three key components: (1) a domain-specific failure taxonomy derived from analyzing real agent failures, (2) an automatic annotation system that classifies failures using defined annotation schema, (3) a hybrid explanation generator that produces visual execution flows, natural language explanations, and actionable recommendations. Through a user study with 20 participants (10 technical, 10 non-technical), we demonstrate that our approach enables users to identify failure root causes 2.8 times faster and propose correct fixes with 73% higher accuracy compared to raw execution traces. Importantly, our structured approach outperforms ad-hoc state of the art models explanations by providing consistent, domain-specific insights with integrated visualizations. Our work establishes a framework for systematic agent failure analysis, addressing the critical need for interpretable AI systems in software development workflows</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.SE'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-06T06:18:20Z</published>\n    <arxiv:comment>17 Pages, 3 Figures, 2 Tables</arxiv:comment>\n    <arxiv:primary_category term='cs.SE'/>\n    <author>\n      <name>Arun Joshi</name>\n    </author>\n  </entry>"
}