Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2501.06625 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915099114995712 |
|---|---|
| author | Almorsi, Amr Ahmed, Mohanned Gomaa, Walid |
| author_facet | Almorsi, Amr Ahmed, Mohanned Gomaa, Walid |
| contents | Large Language Models (LLMs) have shown remarkable capabilities in code generation tasks, yet they face significant limitations in handling complex, long-context programming challenges and demonstrating complex compositional reasoning abilities. This paper introduces a novel agentic framework for ``guided code generation'' that tries to address these limitations through a deliberately structured, fine-grained approach to code generation tasks. Our framework leverages LLMs' strengths as fuzzy searchers and approximate information retrievers while mitigating their weaknesses in long sequential reasoning and long-context understanding. Empirical evaluation using OpenAI's HumanEval benchmark with Meta's Llama 3.1 8B model (int4 precision) demonstrates a 23.79\% improvement in solution accuracy compared to direct one-shot generation. Our results indicate that structured, guided approaches to code generation can significantly enhance the practical utility of LLMs in software development while overcoming their inherent limitations in compositional reasoning and context handling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_06625 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Guided Code Generation with LLMs: A Multi-Agent Framework for Complex Code Tasks Almorsi, Amr Ahmed, Mohanned Gomaa, Walid Artificial Intelligence Large Language Models (LLMs) have shown remarkable capabilities in code generation tasks, yet they face significant limitations in handling complex, long-context programming challenges and demonstrating complex compositional reasoning abilities. This paper introduces a novel agentic framework for ``guided code generation'' that tries to address these limitations through a deliberately structured, fine-grained approach to code generation tasks. Our framework leverages LLMs' strengths as fuzzy searchers and approximate information retrievers while mitigating their weaknesses in long sequential reasoning and long-context understanding. Empirical evaluation using OpenAI's HumanEval benchmark with Meta's Llama 3.1 8B model (int4 precision) demonstrates a 23.79\% improvement in solution accuracy compared to direct one-shot generation. Our results indicate that structured, guided approaches to code generation can significantly enhance the practical utility of LLMs in software development while overcoming their inherent limitations in compositional reasoning and context handling. |
| title | Guided Code Generation with LLMs: A Multi-Agent Framework for Complex Code Tasks |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2501.06625 |