Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Aofan, Li, Haoxuan, Wang, Bin, Yang, Ao, Li, Hui
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.08665
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918157815382016
author Liu, Aofan
Li, Haoxuan
Wang, Bin
Yang, Ao
Li, Hui
author_facet Liu, Aofan
Li, Haoxuan
Wang, Bin
Yang, Ao
Li, Hui
contents Code generation models based on large language models (LLMs) have gained wide adoption, but challenges remain in ensuring safety, accuracy, and controllability, especially for complex tasks. Existing methods often lack dynamic integration of external tools, transparent reasoning, and user control over safety. To address these issues, we propose a controllable code generation framework utilizing the ReAct paradigm for multi-agent task execution. This framework is a multi-agent system designed to enable efficient, precise, and interpretable code generation through dynamic interactions between LLMs and external resources. The framework adopts a collaborative architecture comprising four specialized agents: a Planner for task decomposition, a Searcher that leverages the ReAct framework for reasoning and tool integration, a CodeGen agent for accurate code generation, and an Extractor for structured data retrieval. The ReAct-based Searcher alternates between generating reasoning traces and executing actions, facilitating seamless integration of internal knowledge with external tools (such as search engines) to enhance accuracy and user control. Experimental results show the framework's effectiveness across multiple languages, achieving a 94.8% security rate on the SVEN dataset with CodeQL, outperforming existing approaches. Its transparent reasoning process fosters user trust and improves controllability.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08665
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution
Liu, Aofan
Li, Haoxuan
Wang, Bin
Yang, Ao
Li, Hui
Software Engineering
Artificial Intelligence
Code generation models based on large language models (LLMs) have gained wide adoption, but challenges remain in ensuring safety, accuracy, and controllability, especially for complex tasks. Existing methods often lack dynamic integration of external tools, transparent reasoning, and user control over safety. To address these issues, we propose a controllable code generation framework utilizing the ReAct paradigm for multi-agent task execution. This framework is a multi-agent system designed to enable efficient, precise, and interpretable code generation through dynamic interactions between LLMs and external resources. The framework adopts a collaborative architecture comprising four specialized agents: a Planner for task decomposition, a Searcher that leverages the ReAct framework for reasoning and tool integration, a CodeGen agent for accurate code generation, and an Extractor for structured data retrieval. The ReAct-based Searcher alternates between generating reasoning traces and executing actions, facilitating seamless integration of internal knowledge with external tools (such as search engines) to enhance accuracy and user control. Experimental results show the framework's effectiveness across multiple languages, achieving a 94.8% security rate on the SVEN dataset with CodeQL, outperforming existing approaches. Its transparent reasoning process fosters user trust and improves controllability.
title RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2510.08665