We present Dyve, a dynamic process verifier that enhances reasoning error detection in large language models by integrating fast and slow thinking, inspired by Kahneman's Systems Theory. Dyve adaptively applies immediate token-level confirmation System 1 for straightforward steps and comprehensive analysis System 2 for complex ones. Leveraging a novel step-wise consensus-filtered process supervision technique, combining Monte Carlo estimation with LLM based evaluation, Dyve curates high-quality supervision signals from noisy data. Experimental results on ProcessBench and the MATH dataset confirm that Dyve significantly outperforms existing process-based verifiers and boosts performance in Best-of-N settings.
@article{arxiv.2502.11157,
title = {Dyve: Thinking Fast and Slow for Dynamic Process Verification},
author = {Jianyuan Zhong and Zeju Li and Zhijian Xu and Xiangyu Wen and Qiang Xu},
journal= {arXiv preprint arXiv:2502.11157},
year = {2025}
}