Context Matters: Improving the Practical Reliability of LLM-Based Unit Test Generation

• URL: http://arxiv.org/abs/2607.19682v1
• Date: Wed, 22 Jul 2026 02:31:10 GMT
• Title: Context Matters: Improving the Practical Reliability of LLM-Based Unit Test Generation
• Abstract summary: This paper reports our experience in designing, deploying, and evaluating CATGen, a context-aware unit test generation workflow.<n>Rather than relying on LLMs to infer incomplete project context, we found that compilation robustness critically depends on making project-level dependencies explicit.<n>We evaluate CATGen on real-world complex focal methods from proprietary industrial projects and additionally on the Defects4J benchmark to assess generalizability.
• Score: 19.272036022286844
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automated unit test generation has recently benefited from advances in large language models (LLMs), yet our industrial deployments reveal a persistent gap between promising research results and practical usability. In real-world projects with complex frameworks and cross-file dependencies, LLM-generated tests frequently fail to compile, require costly manual repair, or provide unstable coverage improvements. This paper reports our experience in designing, deploying, and evaluating CATGen, a context-aware workflow for LLM-based unit test generation, informed by repeated industrial failures and refinements. Rather than relying on LLMs to infer incomplete project context, we found that compilation robustness critically depends on making project-level dependencies explicit, stabilizing test class scaffolding, and replacing iterative LLM-based repair with lightweight static analysis. These experience-driven insights shaped CATGen's multi-stage design, which combines structured context retrieval, deterministic test skeleton construction, and program analysis-based post-processing. We evaluate CATGen on real-world complex focal methods from proprietary industrial projects and additionally on the Defects4J benchmark to assess generalizability. Across both settings, CATGen substantially improves compilation success and structural coverage while significantly reducing generation time and token consumption compared to existing LLM-based approaches. Our results demonstrate that reliable LLM-based unit test generation in practice depends less on prompt engineering alone and more on systematic engineering support grounded in real-world development constraints.

Related papers

• RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices [54.956760584923295]
  Researchers have made substantial progress using Large Language Models (LLMs) for code generation.<n>However, developers typically write code based on structured designs or specifications rather than raw natural language descriptions.<n>This gap between existing benchmarks and real industry development practices means that current benchmark scores may not accurately reflect how much code generation can help automate development tasks.
  arXiv  Detail & Related papers  (2026-04-24T15:35:54Z)
• Call-Chain-Aware LLM-Based Test Generation for Java Projects [7.5943459078703475]
  We present CAT, a call-chain-aware test generation approach that explicitly incorporates call-chain and dependency contexts into prompts.<n>We evaluate CAT on the widely used Defects4J benchmark and on four real-world GitHub projects released after the LLM's cut-off date.<n>The results show that, across projects in Defects4J, CAT improves line and branch coverage by 18.04% and 21.74%, respectively, over the state-of-the-art approach PANTA.
  arXiv  Detail & Related papers  (2026-04-23T20:03:18Z)
• LLMs taking shortcuts in test generation: A study with SAP HANA and LevelDB [0.22940141855172033]
  Large Language Models (LLMs) have achieved impressive results on public benchmarks, often leading to claims of advanced reasoning.<n>This paper investigates behavior in automated test generation for software memorization, contrasting performance on an open-source system.<n>Results show that LLMs excel on familiar, open-source benchmarks but struggle with unseen, complex, often prioritizing compilability over effectiveness.
  arXiv  Detail & Related papers  (2026-04-15T21:30:02Z)
• Failure Modes in LLM Systems: A System-Level Taxonomy for Reliable AI Applications [0.0]
  Large language models (LLMs) are being rapidly integrated into decision-support tools, automation, and AI-enabled software systems.<n>This paper presents a system-level taxonomy of fifteen hidden failure modes that arise in real-world LLM applications.
  arXiv  Detail & Related papers  (2025-11-25T05:19:23Z)
• Training Language Models to Generate Quality Code with Program Analysis Feedback [66.0854002147103]
  Code generation with large language models (LLMs) is increasingly adopted in production but fails to ensure code quality.<n>We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code.
  arXiv  Detail & Related papers  (2025-05-28T17:57:47Z)
• MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering [57.156093929365255]
  Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents.<n>MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios.<n>Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-12T17:35:43Z)
• Evaluating Large Language Models for Real-World Engineering Tasks [75.97299249823972]
  This paper introduces a curated database comprising over 100 questions derived from authentic, production-oriented engineering scenarios.<n>Using this dataset, we evaluate four state-of-the-art Large Language Models (LLMs)<n>Our results show that LLMs demonstrate strengths in basic temporal and structural reasoning but struggle significantly with abstract reasoning, formal modeling, and context-sensitive engineering logic.
  arXiv  Detail & Related papers  (2025-05-12T14:05:23Z)
• APE-Bench I: Towards File-level Automated Proof Engineering of Formal Math Libraries [5.227446378450704]
  APE-Bench I is the first realistic benchmark built from real-world commit histories of Mathlib4.<n>Eleanstic is a scalable parallel verification infrastructure optimized for proof checking across multiple versions of Mathlib.
  arXiv  Detail & Related papers  (2025-04-27T05:04:02Z)
• A Systematic Approach for Assessing Large Language Models' Test Case Generation Capability [0.8287206589886879]
  We propose the Generated Benchmark from Control-Flow Structure and Variable Usage Composition (GBCV) approach to evaluate large language models (LLMs)<n>By leveraging basic control-flow structures and variable usage, GBCV provides a flexible framework to create a spectrum of programs ranging from simple to complex.<n>Our findings indicate that GPT-4o performs better on complex program structures, while all models effectively detect boundary values in simple conditions but face challenges with arithmetic computations.
  arXiv  Detail & Related papers  (2025-02-05T03:51:44Z)
• What's Wrong with Your Code Generated by Large Language Models? An Extensive Study [92.62952504133926]
  This study evaluated the performance of three leading closed-source LLMs and six popular open-source LLMs on three commonly used benchmarks.<n>We developed a taxonomy of bugs for incorrect codes and analyzed the root cause for common bug types.<n>We propose a novel training-free iterative method that introduces self-critique, enabling LLMs to critique and correct their generated code.
  arXiv  Detail & Related papers  (2024-07-08T17:27:17Z)
• Advancing Code Coverage: Incorporating Program Analysis with Large Language Models [8.31978033489419]
  We propose TELPA, a novel technique to generate tests that can reach hard-to-cover branches.<n>Our experimental results on 27 open-source Python projects demonstrate that TELPA significantly outperforms the state-of-the-art SBST and LLM-based techniques.
  arXiv  Detail & Related papers  (2024-04-07T14:08:28Z)
• Characterization of Large Language Model Development in the Datacenter [55.9909258342639]
  Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs. We present an in-depth characterization study of a six-month LLM development workload trace collected from our GPU datacenter Acme.
  arXiv  Detail & Related papers  (2024-03-12T13:31:14Z)

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.