Question about TTRL training schedule: reward convergence & test data usage

[tls0523]

Hi, thanks for your excellent work on TTRL — it has been extremely helpful for our research!
I have two questions about the training procedure, and would really appreciate your clarification:

1. Does TTRL training stop when the reward converges?
   In your experiments, do you monitor the reward curve and stop when it reaches convergence / plateau?
   Or do you train for a fixed number of epochs regardless of reward stabilization?

2. Should test data be used only once in TTRL?
   Since TTRL (Test-Time RL) generates rollouts conditioned on a test dataset, is it recommended that:
   each test sample should be used exactly once?
   or is it acceptable that the same test sample appears repeatedly during multiple epochs of training?