DevNous：一种将IT项目管理扎根于非结构化对话的基于LLM的多智能体系统
DevNous: An LLM-Based Multi-Agent System for Grounding IT Project Management in Unstructured Conversation
AI总结：
研究团队提出DevNous，一种基于LLM的多智能体系统，通过集成团队聊天环境自动将非结构化对话转化为结构化IT项目管理工件，并构建了160轮对话的公共基准，实现81.3%的准确率，贡献了架构模式与首个经验基线。
摘要：
将非结构化的团队对话手动翻译为信息技术（IT）项目治理所需的结构化工件，是现代信息系统管理中的关键瓶颈。我们引入了DevNous，一种基于大型语言模型（LLM）的多智能体专家系统，以自动化这一从非结构化到结构化的翻译过程。DevNous直接集成到团队聊天环境中，从非正式对话中识别可执行的意图，并为自动任务形式化和进度摘要合成等核心管理任务管理有状态的多轮工作流。为了定量评估该系统，我们引入了一个包含160个现实交互式对话轮次的新基准。该数据集采用多标签真实值进行手动标注，并已公开提供。在此基准上，DevNous实现了81.3%的精确匹配轮次准确率和0.845的多重集F1分数，为其可行性提供了有力证据。这项工作的主要贡献有两方面：（1）一种经过验证的用于开发环境管理智能体的架构模式，以及（2）针对这一具有挑战性的问题领域引入了首个稳健的经验基线和公共基准数据集。
英文摘要：
The manual translation of unstructured team dialogue into the structured artifacts required for Information Technology (IT) project governance is a critical bottleneck in modern information systems management. We introduce DevNous, a Large Language Model-based (LLM) multi-agent expert system, to automate this unstructured-to-structured translation process. DevNous integrates directly into team chat environments, identifying actionable intents from informal dialogue and managing stateful, multi-turn workflows for core administrative tasks like automated task formalization and progress summary synthesis. To quantitatively evaluate the system, we introduce a new benchmark of 160 realistic, interactive conversational turns. The dataset was manually annotated with a multi-label ground truth and is publicly available. On this benchmark, DevNous achieves an exact match turn accuracy of 81.3\% and a multiset F1-Score of 0.845, providing strong evidence for its viability. The primary contributions of this work are twofold: (1) a validated architectural pattern for developing ambient administrative agents, and (2) the introduction of the first robust empirical baseline and public benchmark dataset for this challenging problem domain.
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。
