English

PyBangla at BLP-2025 Task 2: Enhancing Bangla-to-Python Code Generation with Iterative Self-Correction and Multilingual Agents

Computation and Language 2026-01-01 v1 Artificial Intelligence

Abstract

LLMs excel at code generation from English prompts, but this progress has not extended to low-resource languages. We address Bangla-to-Python code generation by introducing BanglaCodeAct, an agent-based framework that leverages multi-agent prompting and iterative self-correction. Unlike prior approaches relying on task-specific fine-tuning, BanglaCodeAct employs an open-source multilingual LLM within a Thought-Code-Observation loop, enabling dynamic generation, testing, and refinement of code from Bangla instructions. We benchmark several 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 pass@1 accuracy of 94.0\% on the development set and 71.6\% on the blind test set. These results 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 are publicly available at github.com/jahidulzaid/PyBanglaCodeActAgent.

Keywords

Cite

@article{arxiv.2512.23713,
  title  = {PyBangla at BLP-2025 Task 2: Enhancing Bangla-to-Python Code Generation with Iterative Self-Correction and Multilingual Agents},
  author = {Jahidul Islam and Md Ataullha and Saiful Azad},
  journal= {arXiv preprint arXiv:2512.23713},
  year   = {2026}
}

Comments

6 Pages

R2 v1 2026-07-01T08:44:47.278Z