Tencent-Hunyuan / Thinking-Free_Policy_InitializationView on GitHub
The official code of [ICLR 2026] TFPI: Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
60Jan 27, 2026Updated last month

Alternatives and similar repositories for Thinking-Free_Policy_Initialization

Users that are interested in Thinking-Free_Policy_Initialization are comparing it to the libraries listed below

Sorting:

Are these results useful?