SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

• URL: http://arxiv.org/abs/2310.06770v2
• Date: Fri, 5 Apr 2024 18:16:29 GMT
• Title: SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
• Authors: Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, Karthik Narasimhan,
• Abstract summary: SWE-bench is an evaluation framework consisting of $2,294$ software engineering problems drawn from real GitHub issues and corresponding pull requests across $12$ popular Python repositories. We show that both state-of-the-art proprietary models and our fine-tuned model SWE-Llama can resolve only the simplest issues.
• Score: 80.52201658231895
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language models have outpaced our ability to evaluate them effectively, but for their future development it is essential to study the frontier of their capabilities. We find real-world software engineering to be a rich, sustainable, and challenging testbed for evaluating the next generation of language models. To this end, we introduce SWE-bench, an evaluation framework consisting of $2,294$ software engineering problems drawn from real GitHub issues and corresponding pull requests across $12$ popular Python repositories. Given a codebase along with a description of an issue to be resolved, a language model is tasked with editing the codebase to address the issue. Resolving issues in SWE-bench frequently requires understanding and coordinating changes across multiple functions, classes, and even files simultaneously, calling for models to interact with execution environments, process extremely long contexts and perform complex reasoning that goes far beyond traditional code generation tasks. Our evaluations show that both state-of-the-art proprietary models and our fine-tuned model SWE-Llama can resolve only the simplest issues. The best-performing model, Claude 2, is able to solve a mere $1.96$% of the issues. Advances on SWE-bench represent steps towards LMs that are more practical, intelligent, and autonomous.

Related papers

• Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios [13.949319911378826]
  This study evaluated 4,892 patches from 10 top-ranked agents on 500 real-world GitHub issues. No single agent dominated, with 170 issues unresolved, indicating room for improvement. Most agents maintained code reliability and security, avoiding new bugs or vulnerabilities. Some agents increased code complexity, many reduced code duplication and minimized code smells.
  arXiv  Detail & Related papers  (2024-10-16T11:33:57Z)
• SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains? [64.34184587727334]
  We propose SWE-bench Multimodal to evaluate systems on their ability to fix bugs in visual, user-facing JavaScript software. SWE-bench M features 617 task instances collected from 17 JavaScript libraries used for web interface design, diagramming, data visualization, syntax highlighting, and interactive mapping. Our analysis finds that top-performing SWE-bench systems struggle with SWE-bench M, revealing limitations in visual problem-solving and cross-language generalization.
  arXiv  Detail & Related papers  (2024-10-04T18:48:58Z)
• SWE-bench-java: A GitHub Issue Resolving Benchmark for Java [27.226354754864783]
  SWE-bench has been released to evaluate issue resolving capabilities of large language models (LLMs) As a first step toward multilingual support, we have developed a Java version of SWE-bench, called SWE-bench-java. To verify the reliability of SWE-bench-java, we implement a classic method SWE-agent and test several powerful LLMs on it.
  arXiv  Detail & Related papers  (2024-08-26T15:30:05Z)
• Code-Switched Language Identification is Harder Than You Think [69.63439391717691]
  Code switching is a common phenomenon in written and spoken communication. We look at the application of building CS corpora. We make the task more realistic by scaling it to more languages. We reformulate the task as a sentence-level multi-label tagging problem to make it more tractable.
  arXiv  Detail & Related papers  (2024-02-02T15:38:47Z)
• MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks [50.61968901704187]
  We introduce a pioneering framework for MoT instruction tuning, designed to promote the decomposition of tasks into logical sub-tasks and sub-modules. Our investigations reveal that, through the cultivation and utilization of sub-modules, MoTCoder significantly improves both the modularity and correctness of the generated solutions.
  arXiv  Detail & Related papers  (2023-12-26T08:49:57Z)
• BigIssue: A Realistic Bug Localization Benchmark [89.8240118116093]
  BigIssue is a benchmark for realistic bug localization. We provide a general benchmark with a diversity of real and synthetic Java bugs. We hope to advance the state of the art in bug localization, in turn improving APR performance and increasing its applicability to the modern development cycle.
  arXiv  Detail & Related papers  (2022-07-21T20:17:53Z)
• Measuring Coding Challenge Competence With APPS [54.22600767666257]
  We introduce APPS, a benchmark for code generation. Our benchmark includes 10,000 problems, which range from having simple one-line solutions to being substantial algorithmic challenges. Recent models such as GPT-Neo can pass approximately 15% of the test cases of introductory problems.
  arXiv  Detail & Related papers  (2021-05-20T17:58:42Z)

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.