iReDev: A Knowledge-Driven Multi-Agent Framework for Intelligent Requirements Development
Not on the map. Why?
Abstract (arXiv)
Requirements development is a critical phase as it is responsible for providing a clear understanding of what stakeholders need. It involves collaboration among stakeholders to extract explicit requirements and address potential conflicts, which is time-consuming and labor-intensive. Recently, multi-agent systems for software development have attracted much attention. However, existing research provides limited support for requirements development and overlooks the injection of human knowledge into agents and the human-agent collaboration. % To address these issues, this paper proposes a knowledge-driven multi-agent framework for intelligent requirement development, named iReDev. iReDev features: iReDev consists of six knowledge-driven agents to support the entire requirements development. They collaboratively perform various tasks to produce a software requirements specification. iReDev focuses on integrating human knowledge for agents, enabling them to simulate real-world stakeholders. iReDev uses an event-driven communication mechanism based on an artifact pool. Agents continuously monitor the pool and autonomously trigger the next action based on its changes, enabling iReDev to handle new requirements quickly. iReDev introduces a human-in-the-loop mechanism to support human-agent collaboration, ensuring that the generated artifacts align with the expectations of stakeholders. We evaluated the generated artifacts and results show that iReDev outperforms existing baselines in multiple aspects. We further envision three key directions and hope this work can facilitate the development of intelligent requirements development.
Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Jul 2025.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2025: 1; 2026: 5.
6 papers.
- 2025From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligencecited by 15
- 2026The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agentscited by 1
- 2026Agent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and Benchmarkingcited by 1
- 2026QUARE: Quality-Aware Requirements Analysis through Multi-Agent Dialectical Negotiationcited by 0
- 2026ArgRE: Formal Argumentation for Conflict Resolution in Multi-Agent Requirements Negotiationcited by 0
- 2026From Chat to Interview: Agentic Requirements Elicitation with an Experience Ontologycited by 0
- 2026Agent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and Benchmarking7 Oct 2026
- 2026The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents7 Aug 2026
- 2026From Chat to Interview: Agentic Requirements Elicitation with an Experience Ontology7 May 2026
- 2026ArgRE: Formal Argumentation for Conflict Resolution in Multi-Agent Requirements Negotiation25 Apr 2026
- 2026QUARE: Quality-Aware Requirements Analysis through Multi-Agent Dialectical Negotiation12 Mar 2026
- 2025From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence23 Nov 2025