mlsanityData to 7 Oct 2026

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

arXiv 2512.23713 ↗First posted 27 Nov 2025cs.CL cs.AIcited by 0

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 10 of its 13 references that are in the map. First posted on arXiv 27 Nov 2025.

Builds on

10 of 13 references.

References · 10

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  5. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  6. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  7. 2021BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Banglacited by 123
  8. 2022Natural Language to Code Generation in Interactive Data Science Notebookscited by 86
  9. 2024mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generationcited by 32
  10. 2025TigerCoder: A Novel Suite of LLMs for Code Generation in Banglacited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025BanglaForge: LLM Collaboration with Self-Refinement for Bangla Code Generation
  2. 2026Can Large Language Models Implement Agent-Based Models? An ODD-based Replication Study
  3. 2025From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence
  4. 2025Prompt engineering and framework: implementation to increase code reliability based guideline for LLMs
  5. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
  6. 2024Low-Cost Language Models: Survey and Performance Evaluation on Python Code Generation
  7. 2025LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research
  8. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solving