LATIDIA · Robótica

LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation

arXiv:2611.04974v1 Anuncio Tipo: nuevo Resumen: Investigamos la generación automatizada de políticas ejecutables de aprendizaje por refuerzo (RL) para robots a partir de descripciones de tareas en lenguaje natural. En lugar de utilizar grandes conjuntos de datos en lenguaje natural,

La noticia

arXiv:2611.04974v1 Announce Type: new Abstract: We investigate the automated generation of executable robot reinforcement learning (RL) policies from natural-language task descriptions. Rather than using large language models (LLMs) as execution-time decision makers, we use them as designers that construct RL pipelines before deployment, including Markov decision process (MDP) formulation and simulator implementation. We identify a phase-wise structure in this problem: MDP formulation is dependency-structured and sequential, whereas simulator implementation becomes modular once the formulation is fixed. Based on this structure, we propose ARPG, a dependency-aware agentic framework that performs sequential MDP modeling, localized verification and correction, and simulator-structured implementation while externalizing intermediate artifacts. ARPG targets a key failure mode of