TimeThink: Eliciting Compositional Reasoning in Timeseries Large Language Models
TimeThink, a synthetic framework for eliciting compositional timeseries reasoning that employs a reinforcement learning with verifiable rewards (RLVR) training strategy that encourages explicit reasoning, significantly outperforms strong baselines on both synthetic and real-world benchmarks.
Sudarshan Regmi, Arvind Pillai, Y. Wu et al.
· 0 citations