DevNous: An LLM-Based Multi-Agent System for Grounding IT Project Management in Unstructured Conversation
This addresses a critical bottleneck in IT project governance by automating administrative tasks from informal conversations, though it is incremental as it applies existing LLM methods to a new domain.
The paper tackles automating the translation of unstructured team dialogue into structured artifacts for IT project management, introducing DevNous, an LLM-based multi-agent system that achieves 81.3% exact match turn accuracy and a multiset F1-Score of 0.845 on a new benchmark.
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.