Abstract:

Agile development， with its iterative and rapid delivery characteristics， has become a mainstream software development mode. However， it still faces challenges such as unsustainable evolution， difficulty in knowledge retention， and collaboration issues caused by skill disparities. With the rise of Large Language Models （LLMs） and agent-based technologies， an agile enhancement development framework driven by human-multi-agent collaboration was proposed with LangChain as the collaborative core and Retrieval-Augmented Generation （RAG） as the knowledge support. The framework was optimized through three core mechanisms： an architecture design Agent was introduced to generate three differentiated architectural schemes — conservative （adapting to current requirements but requiring long-term refactoring）， innovative （supporting complex， future-oriented implementations）， and balanced （mediating between current and future needs） — which were evaluated using a seven-dimensional quantitative assessment （including scalability） to assist human architects in decision-making， thereby addressing the challenges of insufficient modeling of technical debt sources and predicting architectural evolution. Development artifacts were automatically generated through agents and predefined templates. Role-based modeling， grounded in a knowledge base， defined the functional boundaries and execution standards of agents， precisely matching tasks with capabilities to reduce collaboration bottlenecks. Experimental results on a portal website project demonstrate that， compared with traditional Scrum methods， the proposed framework reduces development cycle time by 29.6%， decreases defect density by 46.9%， and improves user satisfaction by 16.5%， effectively validating its engineering value and promotion potential in enhancing automation and knowledge management， while ensuring delivery efficiency and system quality.

Key words: agile enhanced development, Large Language Model (LLM), evolution of human-machine collaborative architecture, automated generation of artifacts, standardization of agent roles

摘要：

敏捷开发具有迭代与快速交付的特性，已成为主流的软件开发模式，但仍面临架构不可持续演进、知识难沉淀和能力差异引发协作问题等挑战。随着大语言模型（LLM）与智能体技术的兴起，提出一种以LangChain为协同中枢、检索增强生成（RAG）为知识支撑的人-多智能体协同驱动的敏捷增强开发框架。该框架依托三大核心实现优化：引入架构设计Agent，生成三类差异化的架构方案（保守型适配当前需求但长期需重构，创新型落地复杂但适配未来，折中型平衡当前与未来），结合可拓展性等七维量化评估以辅助人类架构师决策，解决技术债务源头建模不足与架构演进预测难题；通过Agent与预设模板自动化生成开发工件；基于知识库的角色化建模明确智能体功能边界与执行标准，精准匹配任务与能力以减少协作阻塞。基于门户网站项目的实验结果表明：与传统的Scrum方法相比，该框架使开发周期缩短29.6%，缺陷密度降低46.9%，用户满意度提升16.5%，有效验证了它在提升自动化与知识化水平、保证交付效率与系统质量方面的工程价值与推广潜力。

关键词: 敏捷增强开发, 大语言模型, 人机协同架构演化, 工件自动化生成, Agent角色标准化