{"slug": "rethinking-the-value-of-generated-tests-for-llm-software-engineering-agents", "title": "Rethinking the Value of Generated Tests for LLM Software Engineering Agents", "summary": "A new study analyzing six large language models on the SWE-bench Verified benchmark found that agent-written tests do not significantly improve issue resolution rates, despite being a common practice. Researchers observed that GPT-5.2 achieved top-tier performance while writing almost no new tests, and that prompt-induced changes in test-writing volume failed to meaningfully alter final outcomes. The findings suggest that current agent-generated testing practices primarily increase process costs and interaction budgets rather than improving task results.", "body_md": "# Computer Science > Software Engineering\n\n[Submitted on 8 Feb 2026 (\n\n[v1](https://arxiv.org/abs/2602.07900v1)), last revised 9 Apr 2026 (this version, v2)]# Title:Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents\n\n[View PDF](/pdf/2602.07900)\n\n[HTML (experimental)](https://arxiv.org/html/2602.07900v2)\n\nAbstract:Large Language Model (LLM) code agents increasingly resolve repository-level issues by iteratively editing code, invoking tools, and validating candidate patches. In these workflows, agents often write tests on the fly, but the value of this behavior remains unclear. For example, GPT-5.2 writes almost no new tests yet achieves performance comparable to top-ranking[this http URL]raises a central question: do such tests meaningfully improve issue resolution, or do they mainly mimic a familiar software-development practice while consuming interaction budget?\n\nTo better understand the role of agent-written tests, we analyze trajectories produced by six strong LLMs on SWE-bench Verified. Our results show that test writing is common, but resolved and unresolved tasks within the same model exhibit similar test-writing frequencies. When tests are written, they mainly serve as observational feedback channels, with value-revealing print statements appearing much more often than assertion-based checks. Based on these insights, we perform a prompt-intervention study by revising the prompts used with four models to either increase or reduce test writing. The results suggest that prompt-induced changes in the volume of agent-written tests do not significantly change final outcomes in this setting. Taken together, these results suggest that current agent-written testing practices reshape process and cost more than final task outcomes.\n\n## Submission history\n\nFrom: Zhi Chen [[view email](/show-email/c1d11f2e/2602.07900)]\n\n**Sun, 8 Feb 2026 10:26:31 UTC (372 KB)**\n\n[[v1]](/abs/2602.07900v1)**[v2]** Thu, 9 Apr 2026 13:23:28 UTC (1,239 KB)\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/rethinking-the-value-of-generated-tests-for-llm-software-engineering-agents", "canonical_source": "https://arxiv.org/abs/2602.07900", "published_at": "2026-06-06 01:39:40+00:00", "updated_at": "2026-06-06 01:46:44.919915+00:00", "lang": "en", "topics": ["large-language-models", "ai-agents", "ai-research"], "entities": ["GPT-5.2", "SWE-bench Verified"], "alternates": {"html": "https://wpnews.pro/news/rethinking-the-value-of-generated-tests-for-llm-software-engineering-agents", "markdown": "https://wpnews.pro/news/rethinking-the-value-of-generated-tests-for-llm-software-engineering-agents.md", "text": "https://wpnews.pro/news/rethinking-the-value-of-generated-tests-for-llm-software-engineering-agents.txt", "jsonld": "https://wpnews.pro/news/rethinking-the-value-of-generated-tests-for-llm-software-engineering-agents.jsonld"}}