@inproceedings{islam-etal-2025-pybangla,
title = "{P}y{B}angla at {BLP}-2025 Task 2: Enhancing {B}angla-to-Python Code Generation with Iterative Self-Correction and Multilingual Agents",
author = "Islam, Jahidul and
Ataullha, Md and
Azad, Saiful",
editor = "Alam, Firoj and
Kar, Sudipta and
Chowdhury, Shammur Absar and
Hassan, Naeemul and
Prince, Enamul Hoque and
Tasnim, Mohiuddin and
Rony, Md Rashad Al Hasan and
Rahman, Md Tahmid Rahman",
booktitle = "Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "Association for Computational Linguistics",
url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.banglalp-1.55/",
pages = "566--570",
ISBN = "979-8-89176-314-2",
abstract = "LLMs excel at code generation from English prompts, but this progress has not extended to low-resource languages. This paper addresses the challenge of Bangla-to-Python code generation by introducing BanglaCodeAct, an agent-based framework that leverages multi-agent prompting and iterative self-correction. Unlike prior approaches that rely on task-specific fine-tuning, BanglaCodeAct employs an open-source multilingual LLM within a Thought{--}Code{--}Observation loop, enabling the system to dynamically generate, test, and refine code from Bangla instructions. We benchmark several prominent small-parameter open-source LLMs and evaluate their effectiveness on the mHumanEval dataset for Bangla NL2Code. Our results show that Qwen3-8B, when deployed with BanglaCodeAct, achieves the best performance, with a pass@1 accuracy of 94.0{\%} on the development set and 71.6{\%} on the blind test set. These findings establish a new benchmark for Bangla-to-Python translation and highlight the potential of agent-based reasoning for reliable code generation in low-resource languages.. Experimental scripts made publicly available at https://github.com/jahidulzaid/PyBanglaCodeActAgent"
}Markdown (Informal)
[PyBangla at BLP-2025 Task 2: Enhancing Bangla-to-Python Code Generation with Iterative Self-Correction and Multilingual Agents](https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.banglalp-1.55/) (Islam et al., BanglaLP 2025)
ACL