多智能体协作生成孟加拉语指令转Python代码，准确率达95.4%。
NALA_MAINZ at BLP-2025 Task 2: A Multi-agent Approach for Bangla Instruction to Python Code Generation
- 用代码生成与调试双智能体分工，仅传递失败测试用例优化效率。
- 在共享任务中实现95.4%的Pass@1得分，排名第一。
- 适合关注低资源语言代码生成的研究者与开发者参考。
本文介绍吉森大学主兹分校在BLP-2025代码生成共享任务中的优胜系统。我们提出一种基于多智能体的流水线方法：首先由代码生成智能体根据输入指令生成初始程序；该候选程序通过提供的单元测试（pytest风格、断言式）执行验证；仅将失败的测试用例传递给调试智能体，后者重新运行测试，提取错误追踪信息，并结合错误提示、当前程序和相关测试用例生成修正方案。采用此方法，我们的提交在共享任务中取得95.4%的Pass@1得分，位列第一。代码已公开。
原文摘要 · Abstract (English)
This paper presents JGU Mainz's winning system for the BLP-2025 Shared Task on Code Generation from Bangla Instructions. We propose a multi-agent-based pipeline. First, a code-generation agent produces an initial solution from the input instruction. The candidate program is then executed against the provided unit tests (pytest-style, assert-based). Only the failing cases are forwarded to a debugger agent, which reruns the tests, extracts error traces, and, conditioning on the error messages, the current program, and the relevant test cases, generates a revised solution. Using this approach, our submission achieved first place in the shared task with a $Pass@1$ score of 95.4. We also make our code public.
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。