LLM-Assisted Empirical Software Engineering: Systematic Literature Review and Research Agenda

TL;DR

This systematic review explores how Large Language Models are used in Empirical Software Engineering, highlighting their applications, benefits, limitations, and gaps to guide responsible future adoption.

Contribution

It provides a comprehensive synthesis of LLM applications in ESE, identifying current practices, challenges, and future research directions.

Findings

69 LLM-assisted tasks identified, mainly in data processing and analysis.

Benefits include improved efficiency and scalability.

Limitations involve hallucinations, inconsistency, and reproducibility issues.

Abstract

Context: Empirical Software Engineering (ESE) faces increasing challenges due to data scale, methodological complexity, and reproducibility concerns. Large Language Models (LLMs) have emerged as promising tools to support empirical workflows, yet their use remains fragmented, with no comprehensive synthesis to guide responsible adoption. Aims: This study analyzes how LLMs are used in ESE, examining supported tasks, phases of the empirical lifecycle, integration into workflows, reported benefits and limitations, and the extent of reproducibility-related reporting. It also identifies gaps and future research directions. Method: We conducted a systematic literature review of peer-reviewed papers (2020-2025) across 12 leading software engineering venues, resulting in 50 primary studies analyzed through qualitative and quantitative synthesis. Results: We identified 69 LLM-assisted tasks, mainly in mining software repositories and controlled experiments, focusing on classification, filtering, and evaluation. LLMs are used across multiple phases but are concentrated in data processing and analysis. Their integration is largely automation-oriented, with limited decision-support use. Benefits emphasize efficiency and scalability, while limitations include hallucinations, inconsistency, prompt sensitivity, and reproducibility issues. Reporting practices are often incomplete. Conclusion: LLM use in ESE is growing but remains automation-driven, with gaps in human-centered integration and transparency. We outline implications and research agenda for responsible use.