India, March 31 -- Reinforcement learning has pioneered a new Scaling paradigm in the post-training phase of large language models, a breakthrough that is increasingly attracting attention from the industry. With the successive release of OpenAI's O-series models and DeepSeek R1, the excellent performance demonstrated by the models fully proves the crucial role of reinforcement learning in the optimization process

In mid-February this year, the Hunyuan team launched the Hunyuan T1-Preview (Hunyuan-Thinker-1-Preview) reasoning model based on the medium-scale Hunyuan base on the Tencent Yuanbao APP, bringing users an ultimate and rapid in-depth thinking experience.

Today, we are very pleased to announce that the in-depth thinking model of...