Home Research AI for Requirements Engineering
Research Theme · 01
← Back to Research

AI for
Requirements Engineering.

Using machine learning, LLMs, and retrieval-augmented generation to automate how software requirements are elicited, analysed, validated, and translated into verifiable system behaviour. The primary focus of the research programme since 2013.

Theme illustration

Theme Overview

What we study

Requirements are the bridge between human intent and software behaviour. When that bridge is built poorly, systems fail — sometimes catastrophically. This theme asks: how can AI help engineers build that bridge more reliably, at scale, in domains where mistakes are costly?

Key research questions

  • ·Can LLMs reliably identify, classify, and validate requirements in natural language documents?
  • ·How can RAG pipelines retrieve relevant standards and regulations to check requirements against?
  • ·Can AI generate test scenarios directly from natural language specifications?
  • ·How do we elicit requirements from unstructured user feedback at scale?
  • ·What are the limits of LLMs in requirements engineering, and where do humans remain essential?

Related Publications

Selected Papers in this Theme.

[Best Paper · IEEE RE'22] 2022 Automated QA for Compliance Requirements
+

Full title: Automated Question Answering for Improved Understanding of Compliance Requirements. One of the earliest applications of transformer-based multi-document QA to regulatory compliance, evaluated on financial and healthcare specifications — predating widespread LLM adoption. 80+ citations.

Google Scholar ↗ · IEEE RE ↗

[ICSE'23 · A*] 2023 AI-Based QA Assistance for Analysing NL Requirements
+

Full title: AI-Based Question Answering Assistance for Analyzing Natural-Language Requirements. Scalable NLP pipeline validated across 1,250+ industrial requirements from eight domains. Open dataset and replication package released. 100+ citations.

Google Scholar ↗

[Best Paper · IEEE RE'19] 2019 Automated Demarcation of Requirements in Textual Specifications
+

Full title: Automated Demarcation of Requirements in Textual Specifications: A Machine Learning Approach. Foundational ML approach for identifying requirements in natural language documents, evaluated on 22 real specifications across 8 domains. A frequently cited benchmark in the field. 200+ citations.

Google Scholar ↗ · IEEE RE ↗

[IEEE RE'24 · A*] 2024 Generating Test Scenarios from NL Requirements Using RAG-Enhanced LLMs
+

One of the first published applications of RAG to requirements engineering in a live industrial setting, developed with automotive industry partners. Demonstrates how retrieval-augmented generation bridges the gap between natural language requirements and executable test scenarios. First author.

Google Scholar ↗

[ACM TOSEM · A*] 2025 Requirements-Driven Automated Software Testing Using LLMs
+

Systematic approach to deriving executable test cases from natural language requirements using LLMs, evaluated in industrial contexts. Led by PhD student Fanyu Wang — published in ACM Transactions on Software Engineering and Methodology.

Google Scholar ↗

[ASE'25 · A*] 2025 Automated Requirements Elicitation from User Feedback Using RAG-Enhanced LLMs
+

Pipeline for extracting structured requirements from unstructured user reviews at scale, applied to app store data across multiple domains.

Google Scholar ↗

Emerging Direction

Agentic AI & Requirements Engineering.

As AI systems move from answering queries to taking autonomous actions — browsing the web, writing and executing code, managing files, calling APIs — the problem of specification becomes dramatically harder. Agentic systems operate across longer horizons, with less human oversight at each step. When they fail, the failure often traces back not to the model, but to an underspecified goal, a missing constraint, or a boundary condition nobody thought to define.

This emerging research direction asks: what does it mean to specify requirements for an agent rather than a function? How do we define, verify, and monitor bounded autonomy? What guardrails are needed when an LLM-powered agent makes decisions that cascade across systems? This research programme is actively building on its RE and responsible AI foundations to address these questions — in collaboration with industry partners operating in high-stakes domains.

Agentic Systems Bounded Autonomy Goal Specification Runtime Guardrails LLM Orchestration Multi-Agent RE

People

Researchers in this Theme.

Primary Supervisor
Requirements-Driven Software Quality Assurance using LLMs
Monash University
Publications: TOSEM, ASE, RE within 1.5 years
Primary Supervisor
Ethics Framework for Generative AI in Healthcare Software
Monash University
Primary Supervisor
Web Portal for Climate Resilient Agricultural Services
Monash University
Romina Etezadi
Associate Supervisor
Requirements-driven Regulatory Compliance
University of Ottawa
Co-supervised with Prof. Lionel Briand
Space PhD (name withheld)
Primary Supervisor
AI-Driven RE for Space Mission Systems
Industry PhD
Dept of Education / Starbound Space Solutions

Related PhD Research

FW Fanyu Wang YH Yutan Huang UH Usman Hyder Patoo

Interested in collaborating or contributing to this research?

Get in Touch →