Open Models Almanac
Methodspost-trainingreinforcement learning algorithm

specific method · filed under post-training

Rollout Routing Replay

Rollout Routing Replay (R3) is a reinforcement-learning training technique for MoE models that reuses the expert routing decisions made during rollout in the training pass.1 It addresses inconsistent expert routing between rollout and training caused by numerical precision issues.2

How this definition was written

Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.

  1. Rollout Routing Replay (R3) [ma2025stabilizing] to train RL using the same routed experts from rollout — MiMo-V2-Flash Technical Report
  2. MoE models suffer from inconsistent expert routing across rollout and training due to numerical precision issues — MiMo-V2-Flash Technical Report

Also called Rollout Routing Replay (R3).

sources
2
models
3
lab adopt it
1
strongest
used

Documented in

Evidence

3 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
used 3
↑