SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering?

• URL: http://arxiv.org/abs/2605.22175v1
• Date: Thu, 21 May 2026 08:45:50 GMT
• Title: SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering?
• Abstract summary: Test suites are indispensable for synthesizing program repair trajectories and for providing precise feedback signals in reinforcement learning.<n>We introduce SWE-Mutation, a benchmark for evaluating LLM-generated test suites.<n>We propose an agentic, language-agnostic framework for automatically generating complex mutants.
• Score: 32.40265738661726
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Evaluating software engineering capabilities has become a core component of modern large language models (LLMs); however, the key bottleneck hindering further scaling lies not in the scarcity of high-quality solutions, but in the lack of high-quality test suites. Test suites are indispensable both for synthesizing program repair trajectories and for providing precise feedback signals in reinforcement learning. Unfortunately, due to the high cost and difficulty of annotation, high-quality test suites have long been hard to obtain, while those automatically generated by LLMs tend to be superficial and lack sufficient discriminative power. As a first step toward constructing high-quality test suites, we introduce SWE-Mutation, a benchmark for evaluating LLM-generated test suites. The benchmark characterizes test suites by introducing systematically mutated solutions that attempt to ``fool'' the test suites and pass validation. We further propose an agentic, language-agnostic framework for automatically generating complex mutants. Our benchmark consists of 2,636 mutated variants derived from 800 original instances and includes a multilingual subset spanning nine programming languages. Experiments on seven LLMs reveal that even DeepSeek-V3.1 achieves only 10.20% verification and 36.15% detection rates, highlighting the inadequacy of current LLMs. Additionally, our agentic mutation strategy enhances realism, reducing average detection rates from 71.04% to 39.81% compared to conventional methods. These findings expose persistent deficiencies in the ability of current LLMs to generate reliable and discriminative test suites.

Related papers

• Correct Code, Vulnerable Dependencies: A Large Scale Measurement Study of LLM-Specified Library Versions [52.50730821321986]
  We present the first large-scale measurement study of version-level risk in large language models (LLMs)<n>We evaluate 10 LLMs on PinTrace, a curated benchmark of 1,000 Stack Overflow programming tasks.<n>Our findings reveal LLM version selection as a first-class, previously overlooked risk surface in LLM-based development.
  arXiv  Detail & Related papers  (2026-05-07T13:52:59Z)
• TestDecision: Sequential Test Suite Generation via Greedy Optimization and Reinforcement Learning [17.157244731153554]
  We formalize test suite generation as a MDP and demonstrate that its objective exhibits monotone submodularity.<n>We propose TestDecision, which transforms LLMs into neural greedy experts.<n>TestDecision significantly outperforms existing advanced methods.
  arXiv  Detail & Related papers  (2026-04-02T09:13:52Z)
• Are Benchmark Tests Strong Enough? Mutation-Guided Diagnosis and Augmentation of Regression Suites [49.16055123488827]
  Insufficiently strong test suites can admit plausible yet semantically incorrect patches, inflating reported success rates.<n>We introduce STING, a framework for targeted test augmentation that uses semantically altered program variants as diagnostic stressors.<n>STING produces 1,014 validated tests spanning 211 instances and increases patch-region line and branch coverage by 10.8% and 9.5%.
  arXiv  Detail & Related papers  (2026-04-02T01:13:40Z)
• Evaluating LLM-Based Test Generation Under Software Evolution [7.140756378584939]
  Large Language Models (LLMs) are increasingly used for automated unit test generation.<n>We present a large-scale empirical study of LLM-based test generation under program changes.
  arXiv  Detail & Related papers  (2026-03-24T17:14:18Z)
• Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning [54.95476453942411]
  Reinforcement learning for code generation relies on verifiable rewards from unit test pass rates.<n>Recent self-play methods unify code and test generation in a single model.<n>Code-A1 achieves code generation performance matching or exceeding models trained on human-annotated tests.
  arXiv  Detail & Related papers  (2026-03-16T17:58:13Z)
• PALM: Synergizing Program Analysis and LLMs to Enhance Rust Unit Test Coverage [14.702182387149547]
  This paper presents PALM, an approach that leverages large language models (LLMs) to enhance the generation of high-coverage unit tests.<n> PALM performs program analysis to identify branching conditions within functions, which are then combined into path constraints.<n>We implement the approach and evaluate it in 15 open-source Rust crates.
  arXiv  Detail & Related papers  (2025-06-10T17:21:21Z)
• Test smells in LLM-Generated Unit Tests [16.061139428298986]
  This paper presents the first multi-benchmark, large-scale analysis of test smell diffusion in LLM-generated unit tests.<n>Our study draws on 20,505 class-level suites from four LLMs (GPT-3.5, GPT-4, Mistral 7B, Mixtral 8x7B), 972 method-level cases from TestBench, 14,469 EvoSuite tests, and 779,585 human-written tests from 34,635 open-source Java projects.
  arXiv  Detail & Related papers  (2024-10-14T15:35:44Z)
• TestART: Improving LLM-based Unit Testing via Co-evolution of Automated Generation and Repair Iteration [7.509927117191286]
  Large language models (LLMs) have demonstrated remarkable capabilities in generating unit test cases.<n>We propose TestART, a novel unit test generation method.<n>TestART improves LLM-based unit testing via co-evolution of automated generation and repair iteration.
  arXiv  Detail & Related papers  (2024-08-06T10:52:41Z)
• Large-scale, Independent and Comprehensive study of the power of LLMs for test case generation [11.517293765116307]
  Unit testing is essential for software reliability, yet manual test creation is time-consuming and often neglected.<n>This study presents the first large-scale empirical evaluation of LLM-generated unit tests at the class level.
  arXiv  Detail & Related papers  (2024-06-28T20:38:41Z)
• Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph [83.90988015005934]
  Uncertainty quantification is a key element of machine learning applications.<n>We introduce a novel benchmark that implements a collection of state-of-the-art UQ baselines.<n>We conduct a large-scale empirical investigation of UQ and normalization techniques across eleven tasks, identifying the most effective approaches.
  arXiv  Detail & Related papers  (2024-06-21T20:06:31Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• OR-Bench: An Over-Refusal Benchmark for Large Language Models [65.34666117785179]
  Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs.<n>This study proposes a novel method for automatically generating large-scale over-refusal datasets.<n>We introduce OR-Bench, the first large-scale over-refusal benchmark.
  arXiv  Detail & Related papers  (2024-05-31T15:44:33Z)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.