Agent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and Benchmarking
Existing LLM-based approaches for software Requirements Engineering (RE) typically rely on basic prompting strategies or rudimentary agent collaboration, under-utilizing the full potential of multi-agent systems.
ProofPaper ↗
Key points
- We present Agent4RE - a self-refining multi-agent RE system that orchestrates specialized agents and incorporates two iterative improvement loops.
- To support evaluation, we construct RE-E2E - a real-world dataset built from human-written requirement specifications, enabling end-to-end assessment of RE workflows.
- Building on this foundation, we further propose two enhanced Agent4RE versions that incorporate either autonomous self-refinement or structured human feedback, and analyze their strengths and limitations across different scenarios.
- Evaluation on 8 Large Language Models (LLMs) demonstrates that all three Agent4RE variants consistently outperform a domain-context-augmented prompting baseline by average 8% in text-based metrics.
Sources (1)
- [1]Agent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and BenchmarkingarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 11:23 AM
Existing LLM-based approaches for software Requirements Engineering (RE) typically rely on basic prompting strategies or rudimentary agent collaboration, under-utilizing the full potential of multi-agent systems.
We present Agent4RE - a self-refining multi-agent RE system that orchestrates specialized agents and incorporates two iterative improvement loops.
Extractive summary: sentences quoted from the sources.