@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://aclanthology.org/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"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="islam-etal-2025-pybangla">
<titleInfo>
<title>PyBangla at BLP-2025 Task 2: Enhancing Bangla-to-Python Code Generation with Iterative Self-Correction and Multilingual Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jahidul</namePart>
<namePart type="family">Islam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="family">Ataullha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saiful</namePart>
<namePart type="family">Azad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudipta</namePart>
<namePart type="family">Kar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naeemul</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enamul</namePart>
<namePart type="given">Hoque</namePart>
<namePart type="family">Prince</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohiuddin</namePart>
<namePart type="family">Tasnim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Rashad</namePart>
<namePart type="given">Al</namePart>
<namePart type="given">Hasan</namePart>
<namePart type="family">Rony</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Tahmid</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-314-2</identifier>
</relatedItem>
<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</abstract>
<identifier type="citekey">islam-etal-2025-pybangla</identifier>
<location>
<url>https://aclanthology.org/2025.banglalp-1.55/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>566</start>
<end>570</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PyBangla at BLP-2025 Task 2: Enhancing Bangla-to-Python Code Generation with Iterative Self-Correction and Multilingual Agents
%A Islam, Jahidul
%A Ataullha, Md
%A Azad, Saiful
%Y Alam, Firoj
%Y Kar, Sudipta
%Y Chowdhury, Shammur Absar
%Y Hassan, Naeemul
%Y Prince, Enamul Hoque
%Y Tasnim, Mohiuddin
%Y Rony, Md Rashad Al Hasan
%Y Rahman, Md Tahmid Rahman
%S Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-314-2
%F islam-etal-2025-pybangla
%X 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
%U https://aclanthology.org/2025.banglalp-1.55/
%P 566-570
Markdown (Informal)
[PyBangla at BLP-2025 Task 2: Enhancing Bangla-to-Python Code Generation with Iterative Self-Correction and Multilingual Agents](https://aclanthology.org/2025.banglalp-1.55/) (Islam et al., BanglaLP 2025)
ACL