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.
Cite
@article{arxiv.2511.16787,
title = {NALA_MAINZ at BLP-2025 Task 2: A Multi-agent Approach for Bangla Instruction to Python Code Generation},
author = {Hossain Shaikh Saadi and Faria Alam and Mario Sanz-Guerrero and Minh Duc Bui and Manuel Mager and Katharina von der Wense},
journal= {arXiv preprint arXiv:2511.16787},
year = {2025}
}
Comments
BLP 2025 Shared Task 2 - Code Generation in Bangla