LATIDIA · Robótica

Adaptación novedosa a través del modelo híbrido de lenguaje grande (LLM): planificación simbólica y aprendizaje de refuerzo guiado por LLM

arXiv:2603.11351v2 Anuncio Tipo: reemplazar Resumen: En entornos dinámicos de mundo abierto, los agentes autónomos a menudo encuentran novedades que dificultan su capacidad de encontrar planes para lograr sus objetivos. En concreto, la tradicióna

La noticia

arXiv:2603.11351v2 Announce Type: replace Abstract: In dynamic open-world environments, autonomous agents often encounter novelties that hinder their ability to find plans to achieve their goals. Specifically, traditional symbolic planners fail to generate plans when the robot's planning domain lacks the operators that enable it to interact appropriately with novel objects in the environment. We propose a neuro-symbolic architecture that integrates symbolic planning, reinforcement learning, and a large language model (LLM) to learn how to handle novel objects. In particular, we leverage the common sense reasoning capability of the LLM to identify missing operators, generate plans with the symbolic AI planner, and write reward functions to guide the reinforcement learning agent