Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2504.01588 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916671671762944 |
|---|---|
| author | Garello, Luca Belgiovine, Giulia Russo, Gabriele Rea, Francesco Sciutti, Alessandra |
| author_facet | Garello, Luca Belgiovine, Giulia Russo, Gabriele Rea, Francesco Sciutti, Alessandra |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_01588 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Building Knowledge from Interactions: An LLM-Based Architecture for Adaptive Tutoring and Social Reasoning Garello, Luca Belgiovine, Giulia Russo, Gabriele Rea, Francesco Sciutti, Alessandra Robotics Artificial Intelligence 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. |
| title | Building Knowledge from Interactions: An LLM-Based Architecture for Adaptive Tutoring and Social Reasoning |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2504.01588 |