PRefLexOR: preference-based recursive language modeling for exploratory optimization of reasoning and agentic thinking
Crossref DOI link: https://doi.org/10.1038/s44387-025-00003-z
Published Online: 2025-05-14
Update policy: https://doi.org/10.1007/springer_crossmark_policy
Buehler, Markus J.
Text and Data Mining valid from 2025-05-14
Version of Record valid from 2025-05-14
Article History
Received: 1 November 2024
Accepted: 22 March 2025
First Online: 14 May 2025
Competing interests
: The author declares no competing interests.