mlsanityData to 7 Oct 2026

NALA_MAINZ at BLP-2025 Task 2: A Multi-agent Approach for Bangla Instruction to Python Code Generation

arXiv 2511.16787 ↗First posted 20 Nov 2025cs.CL cs.SEcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper presents JGU Mainz's winning system for the BLP-2025 Shared Task on Code Generation from Bangla Instructions. We propose a multi-agent-based pipeline. First, a code-generation agent produces an initial solution from the input instruction. The candidate program is then executed against the provided unit tests (pytest-style, assert-based). Only the failing cases are forwarded to a debugger agent, which reruns the tests, extracts error traces, and, conditioning on the error messages, the current program, and the relevant test cases, generates a revised solution. Using this approach, our submission achieved first place in the shared task with a Pass@1 score of 95.4. We also make our code public.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 15 references that are in the map. First posted on arXiv 20 Nov 2025.

Builds on

12 of 15 references.

References · 12

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  2. 2021Program Synthesis with Large Language Modelscited by 3,509
  3. 2024A Survey on Large Language Models for Code Generationcited by 646
  4. 2025A Survey on Code Generation with LLM-based Agentscited by 104
  5. 2022MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languagescited by 41
  6. 2024Test-Driven Development for Code Generationcited by 32
  7. 2024mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generationcited by 32
  8. 2021ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generationcited by 31
  9. 2025HardTests: Synthesizing High-Quality Test Cases for LLM Codingcited by 22
  10. 2024PyTester: Deep Reinforcement Learning for Text-to-Testcase Generationcited by 6
  11. 2025TigerCoder: A Novel Suite of LLMs for Code Generation in Banglacited by 6
  12. 2025Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedbackcited by 2

Built on by

Not cited yet.