Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2507.18812 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915408587522048 |
|---|---|
| author | Jia, Yiping Jiang, Zhen Ming Noei, Shayan Zou, Ying |
| author_facet | Jia, Yiping Jiang, Zhen Ming Noei, Shayan Zou, Ying |
| contents | With the widespread adoption of Large Language Models (LLMs) such as GitHub Copilot and ChatGPT, developers increasingly rely on AI-assisted tools to support code generation. While LLMs can generate syntactically correct solutions for well-structured programming tasks, they often struggle with challenges that require iterative debugging, error handling, or adaptation to diverse problem structures. Existing approaches such as fine-tuning or self-repair strategies either require costly retraining or lack mechanisms to accumulate and reuse knowledge from previous attempts.
To address these limitations, we propose MemoCoder, a multi-agent framework that enables collaborative problem solving and persistent learning from past fixes. At the core of MemoCoder is a Fixing Knowledge Set, which stores successful repairs and supports retrieval for future tasks. A central Mentor Agent supervises the repair process by identifying recurring error patterns and refining high-level fixing strategies, providing a novel supervisory role that guides the self-repair loop. We evaluate MemoCoder across three public benchmarks -- MBPP, HumanEval, and LiveCodeBench -- spanning a range of problem complexities. Experimental results show that MemoCoder consistently outperforms both zero-shot prompting and a Self-Repair strategy, with improvements ranging from 3.1% to 12.1% in Pass@10 and from 1.4% to 14.5% in Pass@50, demonstrating its effectiveness in iterative refinement and knowledge-guided code generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_18812 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MemoCoder: Automated Function Synthesis using LLM-Supported Agents Jia, Yiping Jiang, Zhen Ming Noei, Shayan Zou, Ying Software Engineering Artificial Intelligence With the widespread adoption of Large Language Models (LLMs) such as GitHub Copilot and ChatGPT, developers increasingly rely on AI-assisted tools to support code generation. While LLMs can generate syntactically correct solutions for well-structured programming tasks, they often struggle with challenges that require iterative debugging, error handling, or adaptation to diverse problem structures. Existing approaches such as fine-tuning or self-repair strategies either require costly retraining or lack mechanisms to accumulate and reuse knowledge from previous attempts. To address these limitations, we propose MemoCoder, a multi-agent framework that enables collaborative problem solving and persistent learning from past fixes. At the core of MemoCoder is a Fixing Knowledge Set, which stores successful repairs and supports retrieval for future tasks. A central Mentor Agent supervises the repair process by identifying recurring error patterns and refining high-level fixing strategies, providing a novel supervisory role that guides the self-repair loop. We evaluate MemoCoder across three public benchmarks -- MBPP, HumanEval, and LiveCodeBench -- spanning a range of problem complexities. Experimental results show that MemoCoder consistently outperforms both zero-shot prompting and a Self-Repair strategy, with improvements ranging from 3.1% to 12.1% in Pass@10 and from 1.4% to 14.5% in Pass@50, demonstrating its effectiveness in iterative refinement and knowledge-guided code generation. |
| title | MemoCoder: Automated Function Synthesis using LLM-Supported Agents |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2507.18812 |