# Enhancing LLM Code Generation Capabilities through Test-Driven Development and Code Interpreter

arXiv: https://arxiv.org/abs/2511.12823 · HTML: https://mlsanity.com/paper/2511.12823/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 16 Nov 2025.

## Builds on (most cited first, 9 of 9)

- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages](https://mlsanity.com/paper/2406.09948/) (2024)
- [Tokenizer Choice For LLM Training: Negligible or Crucial?](https://mlsanity.com/paper/2310.08754/) (2023)
- [BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla](https://mlsanity.com/paper/2205.11081/) (2022)
- [mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generation](https://mlsanity.com/paper/2410.15037/) (2024)
- [TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla](https://mlsanity.com/paper/2509.09101/) (2025)
- [The Transformative Influence of LLMs on Software Development & Developer Productivity](https://mlsanity.com/paper/2311.16429/) (2023)

## Abstract (arXiv)

Over the past few years, improving LLM code generation capabilities has been a key focus in NLP research. Despite Bengali having 242 million native speakers worldwide, it receives little attention when it comes to training LLMs. More recently, various fine-tuning and augmented generation techniques have been employed to significantly enhance code generation performance. However, they require considerable expertise and resources to utilize effectively as an end user. The goal of our work is to democratize access to powerful code generation tools in resource-constrained emerging markets, enabling users to leverage them in their native language. We introduce a novel approach that combines Test-Driven Development (TDD) and Code Interpreter (CI), utilizing open-weight models, which improves the baseline accuracy for code generation with Bengali prompts and achieves an overall accuracy of 85%. Our approach requires no finetuning and proves that even the smallest models in the same family can attain up to 98% accuracy compared to the largest models. All of our results are publicly shared in GitHub for validation and reproducibility.