paper-with-me

Papers

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

2025-11-20 · Hossain Shaikh Saadi, Faria Alam, Mario Sanz-Guerrero, Minh Duc Bui, Manuel Mager, Katharina von der Wense 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.

📄 PDF Abstract BibTeX arXiv:2511.16787

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation

2026-06-28 · Cheng Wan, Yongsen Mao, Wenzheng Wu, Yuxuan Xie 외 arxiv

Recently, Large Language Models (LLMs) have emerged as promising layout agents for 3D scene generation. Existing layout agents still suffer from implausible layout generation because most of them convert 3D assets and 3D…

Scene Generation

JGU Mainz's Submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: MT and QA

2025-09-26 · Hossain Shaikh Saadi, Minh Duc Bui, Mario Sanz-Guerrero, Katharina von der Wense arxiv

This paper presents the JGU Mainz submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: Machine Translation and Question Answering, focusing on Ukrainian, Upper Sorbian, and Lower Sorbi…

Machine TranslationQuestion Answering

Towards Proactive Personalization through Profile Customization for Individual Users in Dialogues

2025-12-17 · Xiaotian Zhang, Yuan Wang, Ruizhe Chen, Zeya Wang 외 arxiv

The deployment of Large Language Models (LLMs) in interactive systems necessitates a deep alignment with the nuanced and dynamic preferences of individual users. Current alignment techniques predominantly address univers…

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

2025-11-27 · Jahidul Islam, Md Ataullha, Saiful Azad 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 le…

Code Generation

Learning to Model the World with Language

2023-07-31 · Jessy Lin, Yuqing Du, Olivia Watkins, Danijar Hafner 외

To interact with humans and act in the world, agents need to understand the range of language that people use and relate it to the visual world. While current agents can learn to execute simple language instructions, we …

Future predictionGeneral KnowledgemodelSelf-Supervised Learning