Research

Paper

AI LLM March 04, 2026

SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration

Authors

Jialong Chen, Xander Xu, Hu Wei, Chuan Chen, Bing Zhao

Abstract

Large language model (LLM)-powered agents have demonstrated strong capabilities in automating software engineering tasks such as static bug fixing, as evidenced by benchmarks like SWE-bench. However, in the real world, the development of mature software is typically predicated on complex requirement changes and long-term feature iterations -- a process that static, one-shot repair paradigms fail to capture. To bridge this gap, we propose \textbf{SWE-CI}, the first repository-level benchmark built upon the Continuous Integration loop, aiming to shift the evaluation paradigm for code generation from static, short-term \textit{functional correctness} toward dynamic, long-term \textit{maintainability}. The benchmark comprises 100 tasks, each corresponding on average to an evolution history spanning 233 days and 71 consecutive commits in a real-world code repository. SWE-CI requires agents to systematically resolve these tasks through dozens of rounds of analysis and coding iterations. SWE-CI provides valuable insights into how well agents can sustain code quality throughout long-term evolution.

Metadata

arXiv ID: 2603.03823
Provider: ARXIV
Primary Category: cs.SE
Published: 2026-03-04
Fetched: 2026-03-05 06:06

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.03823v1</id>\n    <title>SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration</title>\n    <updated>2026-03-04T08:20:25Z</updated>\n    <link href='https://arxiv.org/abs/2603.03823v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.03823v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Large language model (LLM)-powered agents have demonstrated strong capabilities in automating software engineering tasks such as static bug fixing, as evidenced by benchmarks like SWE-bench. However, in the real world, the development of mature software is typically predicated on complex requirement changes and long-term feature iterations -- a process that static, one-shot repair paradigms fail to capture. To bridge this gap, we propose \\textbf{SWE-CI}, the first repository-level benchmark built upon the Continuous Integration loop, aiming to shift the evaluation paradigm for code generation from static, short-term \\textit{functional correctness} toward dynamic, long-term \\textit{maintainability}. The benchmark comprises 100 tasks, each corresponding on average to an evolution history spanning 233 days and 71 consecutive commits in a real-world code repository. SWE-CI requires agents to systematically resolve these tasks through dozens of rounds of analysis and coding iterations. SWE-CI provides valuable insights into how well agents can sustain code quality throughout long-term evolution.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.SE'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-03-04T08:20:25Z</published>\n    <arxiv:primary_category term='cs.SE'/>\n    <author>\n      <name>Jialong Chen</name>\n    </author>\n    <author>\n      <name>Xander Xu</name>\n    </author>\n    <author>\n      <name>Hu Wei</name>\n    </author>\n    <author>\n      <name>Chuan Chen</name>\n    </author>\n    <author>\n      <name>Bing Zhao</name>\n    </author>\n  </entry>"
}