Agyn：基于团队的自主软件工程多智能体系统
Agyn: A Multi-Agent System for Team-Based Autonomous Software Engineering
AI总结：
Agyn提出了一种基于团队结构的多智能体系统，通过模拟工程团队的组织过程和协作方法，实现自主软件工程任务的高效处理。
摘要：
大型语言模型在个体软件工程任务中展现了强大的能力，但大多数自主系统仍将问题解决视为单一或流水线式的过程。相比之下，现实中的软件开发是由团队按照共享的方法论进行协作活动，具有明确的角色分工、沟通和审查。在本工作中，我们提出了一种完全自动化的多智能体系统，明确地将软件工程建模为一个组织过程，复制了工程团队的结构。基于agyn，一个开源的配置智能体团队平台，我们的系统为协调、研究、实现和审查等角色分配了专门的智能体，并为它们提供隔离的沙箱进行实验，并启用结构化的沟通。该系统遵循定义的开发方法论来处理问题，包括分析、任务规格、拉取请求创建和迭代审查，并且在没有人工干预的情况下运行。重要的是，该系统是为真实生产使用而设计的，而不是针对SWE-bench进行调优。在post hoc评估SWE-bench 500上，它解决了72.2%的任务，优于使用相似语言模型的单智能体基线。我们的结果表明，复制团队结构、方法论和沟通是一种强大的自主软件工程范式，未来进展可能同样取决于组织设计和智能体基础设施，而不仅仅是模型改进。
英文摘要：
Large language models have demonstrated strong capabilities in individual software engineering tasks, yet most autonomous systems still treat issue resolution as a monolithic or pipeline-based process. In contrast, real-world software development is organized as a collaborative activity carried out by teams following shared methodologies, with clear role separation, communication, and review. In this work, we present a fully automated multi-agent system that explicitly models software engineering as an organizational process, replicating the structure of an engineering team. Built on top of agyn, an open-source platform for configuring agent teams, our system assigns specialized agents to roles such as coordination, research, implementation, and review, provides them with isolated sandboxes for experimentation, and enables structured communication. The system follows a defined development methodology for working on issues, including analysis, task specification, pull request creation, and iterative review, and operates without any human intervention. Importantly, the system was designed for real production use and was not tuned for SWE-bench. When evaluated post hoc on SWE-bench 500, it resolves 72.2% of tasks, outperforming single-agent baselines using comparable language models. Our results suggest that replicating team structure, methodology, and communication is a powerful paradigm for autonomous software engineering, and that future progress may depend as much on organizational design and agent infrastructure as on model improvements.
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。
