Towards Long-Horizon Vessel Trajectory and Destination Forecasting with Reasoning Large Language Models
Researchers have developed a new framework called RLVR to improve long-horizon maritime trajectory and destination forecasting using large language models. This approach converts vessel trajectories into semantic textual representations, enabling reinforcement learning to align LLMs with forecasting objectives. Experiments show that LLMs trained with RLVR significantly outperform existing deep learning methods, particularly in predicting destinations accurately, with 4B LLMs demonstrating optimal performance. AI
IMPACT Enhances LLM capabilities for complex, long-term predictive tasks in operational domains like maritime logistics.