What question did this study set out to answer?

The aim is to investigate how Large Language Models (LLMs) are changing the process of requirements elicitation, making it more efficient and less error-prone.

May 11, 2026Open Access

Requirements Elicitation in the Era of LLMs: A Survey on Large Language Models for Automated and Assisted Requirements Elicitation

Key Points

The aim is to investigate how Large Language Models (LLMs) are changing the process of requirements elicitation, making it more efficient and less error-prone.
Categorized approaches into Direct RE and Indirect RE, analyzing five paradigms.
Evaluated real-time question generation, simulated user agents, and privacy-preserving multi-agent systems.
Explored generative script creation for education and lexicon-enhanced PLMs for data mining.
Structured multi-agent systems showed that small, private models can match the performance of large LLMs.
Domain-specific constraints like mistake-avoidance prompting significantly improved outcomes.
Trade-offs were identified between generative flexibility and discriminative precision.

Abstract

Requirements Elicitation (RE) is critical but traditionally manual, costly, and prone to missing latent needs. This survey explores how Artificial Intelligence—particularly Large Language Models (LLMs) and Pre-trained Language Models (PLMs)—is transforming RE. We categorize recent approaches into Direct RE (AI actively elicits) and Indirect RE (AI supports training or mines existing data) by analyzing five distinct paradigms: (1) real-time, mistake-guided question generation for live interviews; (2) simulated user agents for uncovering latent needs; (3) privacy-preserving multi-agent fleets using small LLMs for goal-to-story decomposition; (4) generative script creation for RE education; and (5) lexicon-enhanced PLMs for mining noisy app reviews. Our analysis reveals that structured multi-agent systems enable small, private models to rival large LLMs, while domain-specific constraints (e.g., mistake-avoidance prompting, sentiment lexicons) significantly boost performance over generic fine-tuning. We highlight the trade-offs between generative flexibility and discriminative precision, outlining future directions for hybrid, privacy-aware AI in requirements engineering.

Requirements Elicitation in the Era of LLMs: A Survey on Large Language Models for Automated and Assisted Requirements Elicitation

Key Points

Abstract

Cite This Study