LLM vs. Human Unit Tests: Fault Detection on Real Python Bugs

• URL: http://arxiv.org/abs/2606.08588v1
• Date: Sun, 07 Jun 2026 12:01:44 GMT
• Title: LLM vs. Human Unit Tests: Fault Detection on Real Python Bugs
• Abstract summary: Large language models (LLMs) have shown considerable promise for automated unit test generation.<n>We present an empirical comparison of LLM-generated and human-written unit tests across three complementary Python benchmarks.<n>LLMs generated tests with retrieval-augmented context detect faults in 69% of cases compared to 17.2% for general-purpose human-written tests.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have shown considerable promise for automated unit test generation, yet their practical effectiveness relative to human-written tests remains poorly understood. Existing evaluations commonly rely on coverage-oriented benchmarks that do not assess fault-detection capability directly. We present an empirical comparison of LLM-generated and human-written unit tests across three complementary Python benchmarks: 29 real historical bugs from BugsInPy, a function-level benchmark drawn from python-slugify and packaging, and a controlled paired benchmark. Our generation pipeline couples Gemini 2.5 Flash with a lightweight lexical retrieval mechanism that supplies bug-relevant context at generation time. Across eight quality dimensions, LLM-generated tests with retrieval-augmented context detect faults in 69% of cases compared to 17.2% for general-purpose human-written tests (Fisher's exact, $p < 0.001$, Cohen's $h = 1.10$). Critically, line and branch coverage are nearly identical between the two approaches (84.8% vs. 88.5% and 75.2% vs. 82.1%), confirming that coverage is an insufficient proxy for fault-detection capability. We discuss the conditions under which each approach excels, characterize their complementary strengths, and identify the critical role of retrieval context and reproducible benchmark construction in meaningful test-quality evaluation.

Related papers

• Beyond Test Presence: Assessing the Quality and Robustness of Agent-Generated Tests in Open-Source Projects [2.9713899640333348]
  Integrating AI-powered coding agents into Continuous Integration/Continuous Delivery pipelines has fundamentally altered how software verification is conducted.<n>While these agents successfully automate the test generation, current evaluation benchmarks largely focus on pass-rates rather than the intrinsic quality of the generated tests.<n>We compare 204,673 test artifacts which comprises of 24,941 human-authored files and 179,732 agent-generated files; sourced from the AIDev dataset.
  arXiv  Detail & Related papers  (2026-07-13T18:40:24Z)
• PACE: A Proxy for Agentic Capability Evaluation [60.3743414796937]
  We introduce PACE, a framework that constructs proxy benchmarks by selecting instances from existing non-agentic evaluations.<n>Experiments across 14 models, 4 agentic benchmarks, and 19 non-agentic benchmarks show that PACE-Bench predicts agentic scores with leave-one-out cross-validation (LOOCV) mean absolute error (MAE) under 4%, Spearman correlation above 0.80, and pairwise model-ranking accuracy around 85%, all at much less than 1% of the full agentic evaluation cost.
  arXiv  Detail & Related papers  (2026-07-02T10:59:03Z)
• 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)
• VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection [55.957275374847484]
  VulAgent is a multi-agent vulnerability detection framework based on hypothesis validation.<n>It implements a semantics-sensitive, multi-view detection pipeline, each aligned to a specific analysis perspective.<n>On average, VulAgent improves overall accuracy by 6.6%, increases the correct identification rate of vulnerable--fixed code pairs by up to 450%, and reduces the false positive rate by about 36%.
  arXiv  Detail & Related papers  (2025-09-15T02:25:38Z)
• Benchmarking LLMs for Unit Test Generation from Real-World Functions [34.70460519870186]
  We introduce ULT (UnLeakedTestbench), a new benchmark specifically designed for function-level unit test generation from real-world Python functions.<n>With 3,909 carefully selected function-level tasks, ULT provides a more realistic and challenging evaluation of LLMs' test generation capabilities.<n>Our evaluation results demonstrate that ULT is significantly more challenging.
  arXiv  Detail & Related papers  (2025-08-01T08:08:26Z)
• Quality Assessment of Python Tests Generated by Large Language Models [1.0845500038686533]
  This study investigates the quality of Python test code generated by three Large Language Models: GPT-4o, Amazon Q, and LLama 3.3.<n>We evaluate the structural reliability of test suites generated under two distinct prompt contexts: Text2Code (T2C) and Code2Code (C2C)
  arXiv  Detail & Related papers  (2025-06-17T08:16:15Z)
• Type-aware LLM-based Regression Test Generation for Python Programs [13.631541369653066]
  Test4Py is a novel framework that enhances type correctness in automated test generation for Python.<n>Test4Py integrates an iterative repair procedure that progressively refines generated test cases to improve coverage.<n>In an evaluation on 183 real-world Python modules, Test4Py achieved an average statement coverage of 83.0% and branch coverage of 70.8%.
  arXiv  Detail & Related papers  (2025-03-18T08:07:17Z)
• Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios [49.53589774730807]
  Multimodal large language models (MLLMs) have recently achieved state-of-the-art performance on tasks ranging from visual question answering to video understanding.<n>We reveal a response uncertainty phenomenon: twelve state-of-the-art open-source MLLMs overturn a previously correct answer in 65% of cases after receiving a single deceptive cue.
  arXiv  Detail & Related papers  (2024-11-05T01:11:28Z)
• "Knowing When You Don't Know": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation [90.09260023184932]
  Retrieval-Augmented Generation (RAG) grounds Large Language Model (LLM) output by leveraging external knowledge sources to reduce factual hallucinations. NoMIRACL is a human-annotated dataset for evaluating LLM robustness in RAG across 18 typologically diverse languages. We measure relevance assessment using: (i) hallucination rate, measuring model tendency to hallucinate, when the answer is not present in passages in the non-relevant subset, and (ii) error rate, measuring model inaccuracy to recognize relevant passages in the relevant subset.
  arXiv  Detail & Related papers  (2023-12-18T17:18:04Z)
• Effective Test Generation Using Pre-trained Large Language Models and Mutation Testing [13.743062498008555]
  We introduce MuTAP for improving the effectiveness of test cases generated by Large Language Models (LLMs) in terms of revealing bugs. MuTAP is capable of generating effective test cases in the absence of natural language descriptions of the Program Under Test (PUTs) Our results show that our proposed method is able to detect up to 28% more faulty human-written code snippets.
  arXiv  Detail & Related papers  (2023-08-31T08:48:31Z)
• 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.