$T^5$: Twin-Critic Training for Token-Level Thoughts in Reinforcement Mid-Training
This work proposes tfour, a twin-critic method that calibrates token-level advantages from a single generated trajectory, and describes optimal mixing under the signal-retention constraint and establishes an upper bound on residual mean-induced drift.
Nan Qiao, Ye-Bin Yang, Wei-Nong Wang et al.
· 0 citations