ReasonFlow: Flow Matching that Thinks Step by Step
Trains a flow model to follow continuous states derived from prefixes of worked solutions. At inference, it integrates a trajectory from noise using the question and decodes the final state into an answer.
First public: · Added to this list: November 9, 2026
ACL Anthology release date. Date source.
Cite this paper
Published version
ReasonFlow: Flow Matching that Thinks Step by Step
Bing Yan, Ge Sun, Juan J. de Pablo, Stefano Martiniani, Kyunghyun Cho
Findings of the Association for Computational Linguistics: EMNLP 2026, 2026, pp. 48554-48571.
Explore this approach
Continuous-state reasoning — Use vectors—lists of numbers—to carry intermediate reasoning from one step to the next, instead of selecting a text token at every step. Some methods use the model's hidden states; others combine several candidate token representations.
Alternative generation methods — Change how intermediate steps are generated, revised, or searched—for example, by refining several steps in parallel. Some produce written chains of thought.