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

[[RP_SECTION:sense-interaction-alignment-paradigm|Sense-interaction-alignment paradigm]]

Sam: Large language models are shifting human-robot interaction from rigid automation toward adaptive, socially-grounded intelligence. That's the central argument of a systematic review of eighty-six studies from the 2026 CHI Conference.

Alex: Are we actually moving away from the sense-plan-act model that's dominated robotics for decades?

Sam: That's what the authors argue. They identify a new paradigm they call sense-interaction-alignment. Where traditional robotics mapped sensory input to a fixed execution plan, this approach uses language models to ground reasoning in physical and social context simultaneously. The key architectural shift is replacing static task execution with iterative feedback loops.

Alex: So the model isn't just executing a command—it's interpreting the environment in real time. How does the alignment layer actually work?

Sam: Think of it as a longitudinal performance review built into the system. Rather than hard-coded scripts, the robot uses the language model to perform what the authors call behavioral repair—updating its interaction style based on accumulated social history and user feedback. It's less like following a recipe and more like a colleague who adjusts their communication style after noticing what lands and what doesn't. [[RP_SECTION:safety-and-verification-trade-offs|Safety and verification trade-offs]]

Alex: That makes sense for something like elder care, where a robot needs to learn a specific user's routine over weeks. But doesn't constant adaptation create consistency problems? If the system is always updating, how do you trust it in safety-critical moments?

Sam: That's the central trade-off the paper keeps returning to. The flexibility that enables personalization is exactly what makes verification hard. When behavior is adaptive by design, you lose the clean behavioral envelope that safety analysis depends on. And the authors are candid that current research is still largely exploratory—the field is moving faster than our ability to validate these systems. Standardized metrics for quantifying these risks largely don't exist yet.

Alex: So we have the capability to make robots more socially aware, but we lack the framework to ensure they stay safe and predictable. [[RP_SECTION:taxonomy-and-evaluation-metrics|Taxonomy and evaluation metrics]]

Sam: Precisely. To address that fragmentation, the authors propose a taxonomy organized around three dimensions: modality, morphology, and autonomy. The goal is to give the field a common vocabulary—a way to situate individual studies so results can actually accumulate rather than sit in isolation.

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

Yufeng Wang, Yuan Xu, Anastasia Nikolova, Yuxuan Wang, Jianyu Wang, Chongyang Wang, Xin Tong

Feb 13, 2026·5:19·arxiv·Original Paper

Human-Robot Interaction (HRI)Large Language Models (LLMs)Systematic ReviewSense-Interaction-Alignment FrameworkEmbodied IntelligenceEmbodiment

Listen

5 min

Briefing

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.

The Shift to LLM-Driven HRI

Human-Robot Interaction (HRI) has long struggled to bridge the gap between technical task execution and the unpredictable nature of human social behavior. The emergence of Large Language Models (LLMs) has provided a new cognitive foundation for robots, enabling them to move beyond pre-scripted responses. This systematic review of 86 empirical studies reveals that LLMs are not merely adding conversational capabilities; they are fundamentally reconfiguring the interaction lifecycle.

The Sense-Interaction-Alignment Framework

The authors propose a new framework to categorize how LLMs are being integrated into robotics:

Sense: Robots now use LLMs to move beyond raw metric data, constructing semantic understandings of their physical and social environments. This includes multimodal grounding, where vision and language are fused to interpret complex social cues like intent and emotion.
Interaction: The role of the robot has shifted from a passive tool to an active agent. LLMs enable robots to generate novel social signals, engage in fluid, persona-aware dialogue, and co-create plans with human partners in real-time.
Alignment: Because generative models can hallucinate or drift, this phase focuses on iterative optimization. Through longitudinal memory and multi-level repair mechanisms, robots can now adjust their behavior to remain safe, ethical, and personalized to specific user needs.

Why It Matters

This review highlights that we are at a critical juncture in robotics. While the technical potential of LLMs is immense, the field is currently fragmented. By synthesizing diverse approaches—from humanoid social robots to functional industrial arms—this work provides a roadmap for researchers to move toward more robust, human-centered systems. It underscores that the future of HRI lies in balancing the generative power of LLMs with the physical constraints and ethical responsibilities of embodied agents.

Key Terms and Definitions

Sense-Interaction-Alignment Framework — A conceptual model that organizes LLM-driven HRI into three phases: grounding environmental context, generating agentic social behaviors, and iteratively optimizing for human alignment.
Embodied Intelligence — The capability of a robotic system to perceive, reason, and act within a physical or simulated environment, distinguishing it from disembodied AI agents like standard chatbots.
Multimodal Grounding — The process of linking linguistic concepts from an LLM to physical sensory data, such as visual scenes or spatial relationships, to enable context-aware robotic actions.
Human-in-the-Loop (HITL) — A design strategy where human oversight or feedback is integrated into the robotic system to verify actions, correct errors, or guide the learning process.
Repair Mechanism — A defensive strategy used by robotic systems to detect and recover from failures in task execution, social norms, or ethical alignment to maintain user trust.

How Do We Research Human-Robot Interaction in the Age of Large Language Models? A Systematic Review | Yufeng Wang et al. | ResearchPod

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