How Do We Research Human-Robot Interaction in the Age of Large Language Models? A Systematic Review

TL;DR

A systematic literature search following the PRISMA guideline is conducted, revealing that LLMs are transforming the fundamentals of HRI by reshaping how robots sense context, generate socially grounded interactions, and maintain continuous alignment with human needs in embodied settings.

Abstract

Advances in large language models (LLMs) are profoundly reshaping the field of human-robot interaction (HRI). While prior work has highlighted the technical potential of LLMs, few studies have systematically examined their human-centered impact (e.g., human-oriented understanding, user modeling, and levels of autonomy), making it difficult to consolidate emerging challenges in LLM-driven HRI systems. Therefore, we conducted a systematic literature search following the PRISMA guideline, identifying 86 articles that met our inclusion criteria. Our findings reveal that: (1) LLMs are transforming the fundamentals of HRI by reshaping how robots sense context, generate socially grounded interactions, and maintain continuous alignment with human needs in embodied settings; and (2) current research is largely exploratory, with different studies focusing on different facets of LLM-driven HRI, resulting in wide-ranging choices of experimental setups, study methods, and evaluation metrics. Finally, we identify key design considerations and challenges, offering a coherent overview and guidelines for future research at the intersection of LLMs and HRI.

Figures (11)

• Figure 1: Publication trends of three research domains (LLMs, HRI, LLM-driven HRI) in the ACM digital library from 2015 to 2025 (details of search keywords are provided in Appendix \ref{['section:appendix_A']}).
• Figure 2: Illustration of the four core HRI types in Sheridan’s classification framework: (1) supervisory control; (2) teleoperation; (3) automated vehicles; (4) social interaction.
• Figure 3: PRISMA flow diagram outlining the literature screening and inclusion process for this systematic review.
• Figure 4: Overview of publication venues and years: (a) Distribution of included papers by venue. Venues contributing fewer than two included papers were not reported individually and are grouped under "Other" to ensure a meaningful representation. (b) Annual numbers of included papers.
• Figure 5: The proposed Sense-Interaction-Alignment framework for LLM-driven HRI research. This model adapts classical robotic paradigms to address the unique demands of embodied, social collaboration. It transitions from context grounding (Sense) and generative, multi-agent co-creation (Interaction), to continuous iterative optimization (Alignment).