specific method · filed under post-training
Token-in-token-out (TITO)
Uses token IDs as input and output across the rollout interface to preserve stable action-level correspondence and avoid re-tokenization mismatches.
Also called token-in-token-out, token-in, token-out (TITO) API design, Token-in-Token-out Gateway, Token-in-Token-out (TITO) gateway.
- sources
- 2
- models
- 2
- labs adopt it
- 2
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
Documented in
Evidence
3 spans quoted from the sources, strongest treatment first.
We use a token-in, token-out (TITO) API design for the actors used in our RL training. This ensures that token IDs are stable across multi-turn interactions
First, a Token-in-Token-out (TITO) gateway eliminates re-tokenization mismatches by preserving exact action-level correspondence.
token-in-token-out is critical for asynchronous RL training because it preserves exact action-level correspondence
Filed alongside
Other methods under post-training :: rollout & RL infrastructure.