让AI写代码时实时运行验证，确保每行代码都经得起测试。
AgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software Engineering
- 代码修改前必须通过沙箱执行验证，不可跳过。
- 在SWE-BENCH Lite上解决率40.0%，比单智能体高26-28点。
- 适合需要高可靠性的自动化软件开发场景。
大型语言模型能生成看似合理的代码，但无法验证其正确性。现有多智能体系统或模拟执行，或允许跳过验证。我们提出将执行验证作为核心原则：任何代码变更必须在沙箱环境中成功执行后才能传播。我们构建了AGENTFORGE框架，由规划、编码、测试、调试和评审五个智能体通过共享内存与强制Docker沙箱协作。我们将基于LLM的软件工程形式化为对仓库状态的迭代决策过程，其中执行反馈提供的监督信号强于下一个词概率。AGENTFORGE在SWE-BENCH Lite上达到40.0%的解决率，比单智能体基线提升26–28个百分点。消融实验表明，执行反馈和角色分解各自独立贡献性能提升。该框架开源地址：https://github.com/raja21068/AutoCodeAI。
原文摘要 · Abstract (English)
Large language models generate plausible code but cannot verify correctness. Existing multi-agent systems simulate execution or leave verification optional. We introduce execution-grounded verification as a first-class principle: every code change must survive sandboxed execution before propagation. We instantiate this principle in AGENTFORGE, a multi-agent framework where Planner, Coder, Tester, Debugger, and Critic agents coordinate through shared memory and a mandatory Docker sandbox. We formalize software engineering with LLMs as an iterative decision process over repository states, where execution feedback provides a stronger supervision signal than next-token likelihood. AGENTFORGE achieves 40.0\% resolution on SWE-BENCH Lite, outperforming single-agent baselines by 26--28 points. Ablations confirm that execution feedback and role decomposition each independently drive performance. The framework is open-source at https://github.com/raja21068/AutoCodeAI.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。