DyCoT-RE: Chain-of-Thought-enhanced LLM reward engineering with dual-dynamic optimization for reinforcement learning

Neurocomputing 2026 Open access

Read full text

Authors: Xinning Zhu, Jinxin Du, Longfei Huang, Lunde Chen

DOI: 10.1016/j.neucom.2026.133945

Cited by: 0

References: 3

Fields of Study & Subjects

Safety Systems Engineering in Autonomy Statistical and Computational Modeling Statistical Methods in Clinical Trials

References 3