InfCode: 基于对抗的测试和补丁迭代精炼框架用于可靠的软件问题解决
InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution
AI总结：
InfCode通过对抗多代理框架实现测试和补丁的迭代精炼，以提高软件问题解决的可靠性，实验表明其在SWE-bench Verified上达到79.4%的性能，创下了新的最先进水平。
摘要：
大型语言模型已经推动了软件工程自动化的发展，但解决现实中的软件问题仍然具有挑战性，因为它需要仓库级推理、准确的诊断和强验证信号。现有的基于代理和流水线的方法往往依赖于不足的测试，这可能导致补丁满足验证但未能修复根本缺陷。我们提出了InfCode，一个基于对抗的多代理框架，用于自动化仓库级问题解决。InfCode通过测试补丁生成器和代码补丁生成器之间的对抗交互，迭代地精炼测试和补丁，同时选择器代理识别最可靠的修复方案。该框架在容器化环境中运行，支持真实的仓库检查、修改和验证。在SWE-bench Lite和SWE-bench Verified上使用DeepSeek-V3和Claude 4.5 Sonnet等模型进行实验，结果表明InfCode在多个基准上均优于现有方法。在SWE-bench Verified上，InfCode实现了79.4%的性能，建立了新的最先进水平。我们已将InfCode作为开源项目发布在https://github.com/Tokfinity/InfCode。
英文摘要：
Large language models have advanced software engineering automation, yet resolving real-world software issues remains difficult because it requires repository-level reasoning, accurate diagnostics, and strong verification signals. Existing agent-based and pipeline-based methods often rely on insufficient tests, which can lead to patches that satisfy verification but fail to fix the underlying defect. We present InfCode, an adversarial multi-agent framework for automated repository-level issue resolution. InfCode iteratively refines both tests and patches through adversarial interaction between a Test Patch Generator and a Code Patch Generator, while a Selector agent identifies the most reliable fix. The framework runs inside a containerized environment that supports realistic repository inspection, modification, and validation. Experiments on SWE-bench Lite and SWE-bench Verified using models such as DeepSeek-V3 and Claude 4.5 Sonnet show that InfCode consistently outperforms strong baselines. It achieves 79.4% performance on SWE-bench Verified, establishing a new state-of-the-art. We have released InfCode as an open-source project at https://github.com/Tokfinity/InfCode.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
