REVIEW 9 cited by
MARE: Multi-Agents Collaboration Framework for Requirements Engineering
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Requirements Engineering (RE) is a critical phase in the software development process that generates requirements specifications from stakeholders' needs. Recently, deep learning techniques have been successful in several RE tasks. However, obtaining high-quality requirements specifications requires collaboration across multiple tasks and roles. In this paper, we propose an innovative framework called MARE, which leverages collaboration among large language models (LLMs) throughout the entire RE process. MARE divides the RE process into four tasks: elicitation, modeling, verification, and specification. Each task is conducted by engaging one or two specific agents and each agent can conduct several actions. MARE has five agents and nine actions. To facilitate collaboration between agents, MARE has designed a workspace for agents to upload their generated intermediate requirements artifacts and obtain the information they need. We conduct experiments on five public cases, one dataset, and four new cases created by this work. We compared MARE with three baselines using three widely used metrics for the generated requirements models. Experimental results show that MARE can generate more correct requirements models and outperform the state-of-the-art approaches by 15.4%. For the generated requirements specifications, we conduct a human evaluation in three aspects and provide insights about the quality
Forward citations
Cited by 9 Pith papers
-
Model-Driven Discipline for Multi-Agent LLMs: Requirement-to-Verification Generation of Traceable System Models
A requirement-model-driven multi-agent LLM pipeline generates traceable MDE artefacts and formally checks behaviour models, with multi-agent reliably improving syntactic validity but not semantic accuracy across LLMs.
-
QUARE: Quality-Aware Requirements Analysis through Multi-Agent Dialectical Negotiation
Quality-specialized LLM agents that dialectically negotiate cross-quality conflicts produce more balanced, standards-compliant KAOS requirements than task- or knowledge-decomposed multi-agent RE baselines.
-
UserTrace: User-Level Requirements Generation and Traceability Recovery from Software Project Repositories
UserTrace generates user-level requirements from code repositories and recovers live trace links from requirements to implementation, with evaluations suggesting gains over summarization and traceability baselines.
-
iReDev: A Knowledge-Driven Multi-Agent Framework for Intelligent Requirements Development
A knowledge-driven, event-triggered multi-agent framework called iReDev generates software requirements artifacts that outperform zero-shot prompting, MetaGPT, and Elicitron on ten small projects.
-
Automatic Multi-level Feature Tree Construction for Domain-Specific Reusable Artifacts Management
FTBUILDER automatically constructs hierarchical feature trees for software artifact libraries using embeddings, clustering, and LLM summarization.
-
MAAD: Automate Software Architecture Design through Knowledge-Driven Multi-Agent Collaboration
A multi-agent LLM framework generates software architecture designs and evaluation reports from requirements, claimed to outperform MetaGPT on architectural completeness.
-
Knowledge-Guided Multi-Agent Framework for Automated Requirements Development: A Vision
The paper describes KGMAF, a six-agent LLM-based framework for automated requirements development, and reports a preliminary case study on an insurance management system.
-
A Conceptual Framework for Requirements Engineering of Pretrained-Model-Enabled Systems
A conceptual framework reorganizes requirements engineering for pretrained-model-enabled systems into six activities, based on identified challenges of opaque capabilities, context sensitivity, and continuous evolution.
-
LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunities
A survey of LLM-based multi-agent systems across the software development life cycle, plus a research agenda for orchestration, human coordination, cost, and data.
Discussion (0). Continue with ORCID to comment.