Preprint
Aug 2026
Steering Recurrent Reasoners at Inference Time with Readout Feedback
Readout Feedback (RoFB), a test-time intervention that converts intermediate predictions into token-wise pairwise coupling forces injected into the latent dynamics, is introduced, suggesting that closed-loop steering of latent dynamics can serve as a complementary inference-time control mechanism for recurrent reasoning models.
Shunsuke Kamiya, Masanori Koyama, S. Jeong et al.
· 0 citations