{"slug": "swe-bench-promax-benchmarking-agents-on-large-scale-code-refactoring", "title": "SWE-Bench ProMax: Benchmarking Agents on Large-Scale Code Refactoring", "summary": "Researchers introduced SWE-Bench ProMax, an expert-curated multilingual code refactoring benchmark of 170 instances across seven programming languages, designed to address flaws in existing benchmarks such as SWE-bench Verified, where nearly 60% of unsolved instances contain flawed tests. The benchmark's tasks average 11.4 modified files and 261.6 lines of code per instance, and the best frontier model achieved only a 41.2% resolve rate, confirming it presents a meaningful, unsaturated challenge for current AI coding agents.", "body_md": "# Computer Science > Computation and Language\n\n[Submitted on 10 Aug 2026]\n\n# Title:SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring\n\n[View PDF](/pdf/2608.09802)\n\n[HTML (experimental)](https://arxiv.org/html/2608.09802v1)\n\nAbstract:As AI coding agents take on increasingly complex, long-horizon software engineering tasks, existing benchmarks are rapidly saturating and their evaluation quality has come under serious scrutiny: a recent audit found that nearly 60% of unsolved SWE-bench Verified instances contain flawed tests -- either overly narrow tests that reject correct solutions or overly broad tests that check unstated requirements -- and that frontier models can verbatim reproduce gold patches from training data. Code refactoring, which requires coordinated, behavior-preserving changes across many files, offers a substantially harder and more realistic test of agent capability, yet remains underserved by current benchmarks. We introduce SWE-Bench ProMax, an expert-curated, multilingual code refactoring benchmark of 170 instances drawn from real commits across seven programming languages (Python, Java, TypeScript, Go, C, C++, and Rust). Every instance undergoes rigorous, multi-stage curation that directly addresses the quality problems identified in prior benchmarks: issue descriptions are rewritten from scratch to provide precise, unambiguous specifications, and test suites are manually reviewed to remove overly narrow and overly broad tests. Tasks with insufficient complexity or limited cross-file scope are filtered out, yielding a benchmark of challenging, large-scale refactoring tasks that average 11.4 modified files and 261.6 lines of code per instance, substantially exceeding the scale of existing benchmarks. Experiments with frontier models under two agent scaffolds show that the best model achieves only 41.2% resolve rate, confirming that SWE-Bench ProMax presents a meaningful and unsaturated challenge for current AI coding agents. Our benchmark is available at[this https URL].\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/swe-bench-promax-benchmarking-agents-on-large-scale-code-refactoring", "canonical_source": "https://arxiv.org/abs/2608.09802", "published_at": "2026-08-12 01:59:11+00:00", "updated_at": "2026-08-12 02:10:36.919821+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-research", "ai-agents", "ai-tools"], "entities": ["SWE-Bench ProMax", "SWE-bench Verified"], "alternates": {"html": "https://wpnews.pro/news/swe-bench-promax-benchmarking-agents-on-large-scale-code-refactoring", "markdown": "https://wpnews.pro/news/swe-bench-promax-benchmarking-agents-on-large-scale-code-refactoring.md", "text": "https://wpnews.pro/news/swe-bench-promax-benchmarking-agents-on-large-scale-code-refactoring.txt", "jsonld": "https://wpnews.pro/news/swe-bench-promax-benchmarking-agents-on-large-scale-code-refactoring.jsonld"}}