QUARE: Multi-Agent Negotiation for Balancing Quality Attributes in Requirements Engineering

2026-03-12

AI Summary

This work addresses the challenge in requirements engineering of systematically balancing conflicting quality attributes while staying aligned with stakeholder intent. The authors propose a multi-agent framework comprising five specialized quality agents—focusing on safety, efficiency, greenness, trustworthiness, and responsibility—and a central coordinator. Through a dialectical negotiation protocol, the framework explicitly uncovers and resolves cross-quality conflicts. It integrates topological validation with retrieval-augmented generation (RAG) to automatically produce high-fidelity, verifiable KAOS goal models. Empirical evaluation across multiple benchmarks and industrial case studies demonstrates that the approach achieves 98.2% compliance coverage, 94.9% semantic fidelity, and a verifiability score of 4.96 out of 5.0, while increasing requirement generation volume by 25–43% compared to existing frameworks.

Technology Category

• Knowledge Representation and Reasoning: Qualitative Reasoning
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agreement, Argumentation & Negotiation

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content

Abstract

Requirements engineering (RE) is critical to software success, yet automating it remains challenging because multiple, often conflicting quality attributes must be balanced while preserving stakeholder intent. Existing Large-Language-Model (LLM) approaches predominantly rely on monolithic reasoning or implicit aggregation, limiting their ability to systematically surface and resolve cross-quality conflicts. We present QUARE (Quality-Aware Requirements Engineering), a multi-agent framework that formulates requirements analysis as structured negotiation among five quality-specialized agents (Safety, Efficiency, Green, Trustworthiness, and Responsibility), coordinated by a dedicated orchestrator. QUARE introduces a dialectical negotiation protocol that explicitly exposes inter-quality conflicts and resolves them through iterative proposal, critique, and synthesis. Negotiated outcomes are transformed into structurally sound KAOS goal models via topology validation and verified against industry standards through retrieval-augmented generation (RAG). We evaluate QUARE on five case studies drawn from established RE benchmarks (MARE, iReDev) and an industrial autonomous-driving specification, spanning safety-critical, financial, and information-system domains. Results show that QUARE achieves 98.2% compliance coverage (+105% over both baselines), 94.9% semantic preservation (+2.3 percentage points over the best baseline), and high verifiability (4.96/5.0), while generating 25-43% more requirements than existing multi-agent RE frameworks. These findings suggest that effective RE automation depends less on model scale than on principled architectural decomposition, explicit interaction protocols, and automated verification.

Problem

• requirements engineering
• quality attributes
• conflict resolution
• multi-agent negotiation
• stakeholder intent

Innovation

• multi-agent negotiation
• quality attributes
• structured negotiation protocol
• KAOS goal modeling
• retrieval-augmented generation