Self-Organized Agents：面向超大规模代码生成与优化的 LLM 多智能体框架
Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization
AI总结：
本文提出 SoA 多智能体框架，通过按问题复杂度自动扩展智能体并分工协作，突破上下文长度限制，实现超大规模代码生成与优化，在 HumanEval 上 Pass@1 超过单智能体基线 5%。
摘要：
近期，利用大型语言模型（LLM）智能体进行自动代码生成的进展，使我们更接近自动化软件开发的未来。然而，由于上下文长度的限制，现有单智能体方法在生成和改进大规模、复杂代码库方面存在局限。为应对这一挑战，我们提出 Self-Organized multi-Agent framework（SoA），这是一种新颖的多智能体框架，能够可扩展且高效地生成和优化大规模代码。在 SoA 中，自组织智能体独立运行以生成和修改代码组件，同时无缝协作以构建完整代码库。该框架的一个关键特性是可根据问题复杂度自动增加智能体数量，从而实现动态可扩展性。这使得整体代码量能够随智能体数量无限增长，而每个智能体管理的代码量保持恒定。我们在 HumanEval 基准上评估 SoA，结果表明，与单智能体系统相比，SoA 中每个智能体处理的代码显著更少，但整体生成的代码量大幅增加。此外，SoA 在 Pass@1 准确率上比强大的单智能体基线高出 5%。
英文摘要：
Recent advancements in automatic code generation using large language model (LLM) agent have brought us closer to the future of automated software development. However, existing single-agent approaches face limitations in generating and improving large-scale, complex codebases due to constraints in context length. To tackle this challenge, we propose Self-Organized multi-Agent framework (SoA), a novel multi-agent framework that enables the scalable and efficient generation and optimization of large-scale code. In SoA, self-organized agents operate independently to generate and modify code components while seamlessly collaborating to construct the overall codebase. A key feature of our framework is the automatic multiplication of agents based on problem complexity, allowing for dynamic scalability. This enables the overall code volume to be increased indefinitely according to the number of agents, while the amount of code managed by each agent remains constant. We evaluate SoA on the HumanEval benchmark and demonstrate that, compared to a single-agent system, each agent in SoA handles significantly less code, yet the overall generated code is substantially greater. Moreover, SoA surpasses the powerful single-agent baseline by 5% in terms of Pass@1 accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
