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

2026-02-13

AI Summary

This study addresses the current lack of systematic investigation into the human-centered impacts of large language models (LLMs) in human–robot interaction (HRI), a gap that impedes effective responses to emerging challenges in LLM-driven HRI systems. Guided by PRISMA protocols, the authors conduct a systematic review of 86 studies to comprehensively map how LLMs reshape robotic context awareness, socially grounded interaction generation, and sustained alignment with human needs. The analysis reveals that existing research is predominantly exploratory and methodologically heterogeneous. Building on these insights, the work distills key design principles and core challenges, proposing a unified human-centered design framework and a forward-looking research agenda. This contribution establishes a structured theoretical foundation for LLM-enabled HRI, aiming to bridge the gap between technological potential and human experience.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Large language models for search

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.

Problem

• human-robot interaction
• large language models
• human-centered impact
• systematic review
• LLM-driven HRI

Innovation

• Large Language Models
• Human-Robot Interaction
• Systematic Review
• User Modeling
• Socially Grounded Interaction