A novel approach to repair non-idempotent-outcome tests with an LLM-based agent

Ke, Kaiyao

Permalink

https://hdl.handle.net/2142/129317 Copy

Description

Title

A novel approach to repair non-idempotent-outcome tests with an LLM-based agent

Author(s)

Ke, Kaiyao

Issue Date

2025-05-05

Director of Research (if dissertation) or Advisor (if thesis)

Marinov, Darko

Department of Study

Siebel School Comp & Data Sci

Discipline

Computer Science

Degree Granting Institution

University of Illinois Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Software Testing
• Flaky Tests
• Software Quality Assurance

Abstract

Flaky tests, characterized by inconsistent results across repeated executions, present significant challenges in software testing, especially during regression testing. Recently, there has been emerging research interest in non-idempotent-outcome (NIO) flaky tests—tests that pass on the initial run but fail on subsequent executions within the same environment. Despite progress in utilizing Large Language Models (LLMs) to address flaky tests, existing methods have not tackled NIO flaky tests. The limited context window of LLMs restricts their ability to incorporate relevant source code beyond the test method itself, often overlooking crucial information needed to address state pollution, which is the root cause of NIO flakiness. This thesis introduces NIODebugger, the first framework to utilize an LLM-based agent to repair flaky tests. NIODebugger features a three-phase design: detection, exploration, and fixing. In the detection phase, dynamic analysis collects stack traces and custom test execution logs from multiple test runs, which helps in understanding accumulative state pollution (for example, a counter is 2 during the first rerun and becomes 3 in the second rerun). During the exploration phase, the LLM-based agent provides instructions for extracting relevant source code associated with test flakiness. In the fixing phase, NIODebugger repairs the tests using the information gathered from the previous phases. NIODebugger can be integrated with multiple LLMs, achieving patching success rates ranging from 11.63% to 58.72%. Its best-performing variant, NIODebugger-GPT-4, successfully generated correct patches for 101 out of 172 previously unknown NIO tests across 20 large-scale open-source projects. We submitted pull requests for all generated patches; 58 have been merged, only 1 was rejected, and the remaining 42 are pending. The Java implementation of NIODebugger is provided as a Maven plugin accessible at https://github.com/kaiyaok2/NIOInspector. This thesis is based on the paper “NIODebugger: A Novel Approach to Repair Non-Idempotent-Outcome Tests with LLM-Based Agent” accepted to ICSE ’25.

Graduation Semester

2025-05

Type of Resource

Thesis

Handle URL

https://hdl.handle.net/2142/129317

Copyright and License Information

Copyright 2025 Kaiyao Ke

Owning Collections