#artificial intelligence
Mar 2026
Novelty Adaptation Through Hybrid Large Language Model (LLM)-Symbolic Planning and LLM-guided Reinforcement Learning
This work proposes a neuro-symbolic architecture that integrates symbolic planning, reinforcement learning, and a large language model (LLM) to learn how to handle novel objects and outperforms the state-of-the-art methods in operator discovery as well as operator learning in continuous robotic domains.
Hongxuan Lu, Pierrick Lorang, Timothy R. Duggan et al.
· arXiv.org · 2 citations