Agent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and Benchmarking

arXiv:2610.10628 · cs.SE, cs.AI · Submitted 2026-10-07 · Read on arXiv

cs.SE, cs.AI

Submitted: 2026-10-07

Updated: 2026-10-07

Code: https://github.com/markustyj/Agent4RE_ASE-2026

Project page: https://google.github.io/adk-docs

Terminology

• Benchmarking — 1× in this paper · explained in 4 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes

Sources

• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT
• GPT-4o System Card
• MARE: Multi-Agents Collaboration Framework for Requirements Engineering
• iReDev: A Knowledge-Driven Multi-Agent Framework for Intelligent Requirements Development
• LLMREI: Automating Requirements Elicitation Interviews with LLMs
• Characterizing Datasets for LLM-based Requirements Engineering: A Systematic Mapping Study
• LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunities
• Agent4cs: A Multi-agent System for Code Summarization in Large Hierarchical Codebases
• Qwen3 Technical Report
• Large Language Models (LLMs) for Requirements Engineering (RE): A Systematic Literature Review
• BERTScore: Evaluating Text Generation with BERT

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties