Building Knowledge from Interactions: An LLM-Based Architecture for Adaptive Tutoring and Social Reasoning
Year: 2025
Type: preprint
Abstract: Integrating robotics into everyday scenarios like tutoring or physical training requires robots capable of adaptive, socially engaging, and goal-oriented interactions. While Large Language Models show promise in human-like communication, their standalone use is hindered by memory constraints and contextual incoherence. This work presents a multimodal, cognitively inspired framework that enhances LLM-based autonomous decision-making in social and task-oriented Human-Robot Interaction. Specifically, we develop an LLM-based agent for a robot trainer, balancing social conversation with task guidance and goal-driven motivation. To further enhance autonomy and personalization, we introduce a memory system for selecting, storing and retrieving experiences, facilitating generalized reasoning based on knowledge built across different interactions. A preliminary HRI user study and offline experiments with a synthetic dataset validate our approach, demonstrating the system's ability to manage complex interactions, autonomously drive training tasks, and build and retrieve contextual memories, advancing socially intelligent robotics.
Source: arXiv (Cornell University)
Authors: Garello, Luca, Belgiovine, Giulia, Russo, Gabriele, Rea, Francesco, Sciutti, Alessandra
Language: English
Subfield: Social Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W6979227862
Cites:
Cited by:
Related to: