2 papers
cs.LG2026
A Policy Gradient-Based Sequence-to-Sequence Method for Time Series Prediction
Qi Sima, Xinze Zhang, Yukun Bao +2
Sequence-to-sequence architectures built upon recurrent neural networks have become a standard choice for multi-step-ahead time series prediction. In these models, the decoder prod…
cs.AI2025
What to Ask Next? Probing the Imaginative Reasoning of LLMs with TurtleSoup Puzzles
Mengtao Zhou, Sifan Wu, Huan Zhang +2
We investigate the capacity of Large Language Models (LLMs) for imaginative reasoning--the proactive construction, testing, and revision of hypotheses in information-sparse environ…