Automated Benchmark Generation for Repository-Level Coding Tasks

• URL: http://arxiv.org/abs/2503.07701v1
• Date: Mon, 10 Mar 2025 17:42:49 GMT
• Title: Automated Benchmark Generation for Repository-Level Coding Tasks
• Authors: Konstantinos Vergopoulos, Mark Niklas Müller, Martin Vechev,
• Abstract summary: SetUpAgent is a fully automated system capable of historically accurate dependency setup, test execution, and result parsing.<n>We generate two new datasets: (i) SWEE-Bench an extended version of SWE-Bench encompassing hundreds of repositories, and (ii) SWA-Bench a benchmark focusing on applications rather than libraries.
• Score: 7.305342793164905
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Code Agent development is an extremely active research area, where a reliable performance metric is critical for tracking progress and guiding new developments. This demand is underscored by the meteoric rise in popularity of SWE-Bench. This benchmark challenges code agents to generate patches addressing GitHub issues given the full repository as context. The correctness of generated patches is then evaluated by executing a human-written test suite extracted from the repository after the issue's resolution. However, constructing benchmarks like SWE-Bench requires substantial manual effort to set up historically accurate execution environments for testing. Crucially, this severely limits the number of considered repositories, e.g., just 12 for SWE-Bench. Considering so few repositories, selected for their popularity runs the risk of leading to a distributional mismatch, i.e., the measured performance may not be representative of real-world scenarios potentially misguiding development efforts. In this work, we address this challenge and introduce SetUpAgent, a fully automated system capable of historically accurate dependency setup, test execution, and result parsing. Using SetUpAgent, we generate two new datasets: (i) SWEE-Bench an extended version of SWE-Bench encompassing hundreds of repositories, and (ii) SWA-Bench a benchmark focusing on applications rather than libraries. Comparing these datasets to SWE-Bench with respect to their characteristics and code agent performance, we find significant distributional differences, including lower issue description quality and detail level, higher fix complexity, and most importantly up to 40% lower agent success rates.

Related papers

• SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents [49.73885480071402]
  We introduce SWE-PolyBench, a new benchmark for repository-level, execution-based evaluation of coding agents. SWE-PolyBench contains 2110 instances from 21 repositories and includes tasks in Java (165), JavaScript (1017), TypeScript (729) and Python (199), covering bug fixes, feature additions, and code. Our experiments show that current agents exhibit uneven performances across languages and struggle with complex problems while showing higher performance on simpler tasks.
  arXiv  Detail & Related papers  (2025-04-11T17:08:02Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models. Our framework incorporates two complementary strategies: internal TTC and external TTC. We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• EnvBench: A Benchmark for Automated Environment Setup [76.02998475135824]
  Large Language Models have enabled researchers to focus on practical repository-level tasks in software engineering domain. Existing studies on environment setup introduce innovative agentic strategies, but their evaluation is often based on small datasets. To address this gap, we introduce a comprehensive environment setup benchmark EnvBench.
  arXiv  Detail & Related papers  (2025-03-18T17:19:12Z)
• RAG-Verus: Repository-Level Program Verification with LLMs using Retrieval Augmented Generation [4.934638689939017]
  We introduce RagVerus, a framework that synergizes retrieval-augmented generation with context-aware prompting to automate proof synthesis for multi-module repositories.<n>R RagVerus triples proof pass rates on existing benchmarks under constrained language model budgets.
  arXiv  Detail & Related papers  (2025-02-07T21:30:37Z)
• DI-BENCH: Benchmarking Large Language Models on Dependency Inference with Testable Repositories at Scale [39.92722886613929]
  DI-BENCH is a large-scale benchmark and evaluation framework designed to assess Large Language Models' capability on dependency inference.<n>The benchmark features 581 repositories with testing environments across Python, C#, Rust, and JavaScript.<n>Extensive experiments with textual and execution-based metrics reveal that the current best-performing model achieves only a 42.9% execution pass rate.
  arXiv  Detail & Related papers  (2025-01-23T14:27:11Z)
• The BrowserGym Ecosystem for Web Agent Research [151.90034093362343]
  BrowserGym ecosystem addresses the growing need for efficient evaluation and benchmarking of web agents.<n>We propose an extended BrowserGym-based ecosystem for web agent research, which unifies existing benchmarks from the literature.<n>We conduct the first large-scale, multi-benchmark web agent experiment and compare the performance of 6 state-of-the-art LLMs across 6 popular web agent benchmarks.
  arXiv  Detail & Related papers  (2024-12-06T23:43:59Z)
• 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.<n>No single agent dominated, with 170 issues unresolved, indicating room for improvement.<n>Most agents maintained code reliability and security, avoiding new bugs or vulnerabilities.<n>Some agents increased code complexity, many reduced code duplication and minimized code smells.
  arXiv  Detail & Related papers  (2024-10-16T11:33:57Z)
• Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion? [60.84912551069379]
  We present the Code-Development Benchmark (Codev-Bench), a fine-grained, real-world, repository-level, and developer-centric evaluation framework. Codev-Agent is an agent-based system that automates repository crawling, constructs execution environments, extracts dynamic calling chains from existing unit tests, and generates new test samples to avoid data leakage.
  arXiv  Detail & Related papers  (2024-10-02T09:11:10Z)
• On the Impacts of Contexts on Repository-Level Code Generation [5.641402231731082]
  We present RepoExec, a novel benchmark designed to evaluate repository-level code generation. We focus on three key aspects: executability, functional correctness through comprehensive test case generation, and accurate utilization of cross-file contexts.
  arXiv  Detail & Related papers  (2024-06-17T10:45:22Z)
• How to Understand Whole Software Repository? [64.19431011897515]
  An excellent understanding of the whole repository will be the critical path to Automatic Software Engineering (ASE) We develop a novel method named RepoUnderstander by guiding agents to comprehensively understand the whole repositories. To better utilize the repository-level knowledge, we guide the agents to summarize, analyze, and plan.
  arXiv  Detail & Related papers  (2024-06-03T15:20:06Z)
• CommitBench: A Benchmark for Commit Message Generation [22.03783968903916]
  We show that existing datasets exhibit various problems, such as the quality of the commit selection. We compile a new large-scale dataset, CommitBench, adopting best practices for dataset creation. We use CommitBench to compare existing models and show that other approaches are outperformed by a Transformer model pretrained on source code.
  arXiv  Detail & Related papers  (2024-03-08T09:56:45Z)
• WRENCH: A Comprehensive Benchmark for Weak Supervision [66.82046201714766]
  benchmark consists of 22 varied real-world datasets for classification and sequence tagging. We use benchmark to conduct extensive comparisons over more than 100 method variants to demonstrate its efficacy as a benchmark platform.
  arXiv  Detail & Related papers  (2021-09-23T13:47:16Z)

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.