Rethinking Latent Reasoning for Generative Recommendation: Beyond Teacher-Generated CoT and Recurrent Hidden-State Feedback

Yiwen Chen, Fuwei Zhang, Zehao Chen, Deqing Wang, Hehan Li, Peizhi Xu, Hanmeng Liu, Shuanglong Li, Xin Pei, Fuzhen Zhuang, Zhao Zhang

Adds learned thought tokens between a user’s item history and the next-item prediction. Trains their hidden states to represent keywords from past items, then processes all thought tokens in one prompt pass without generating a written reasoning trace.

First public: November 6, 2026 · Added to this list: November 9, 2026