Laguna-S-2.1
PoolsideWe 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
specific method · filed under post-training
Token-in-Token-out (TITO) is an RL rollout API design in which the training pipeline consumes the exact token IDs and metadata produced by the inference engine instead of finalized text.1 It avoids re-tokenization mismatches in token boundaries, truncation, and special tokens, preserving exact correspondence between sampled actions and what is optimized.2
Trade-off TITO keeps token IDs stable across multi-turn interactions but risks misalignment between RL trajectories and the production chat template.3,4
Summarised by glm-5.3-flash from 2 sources; every sentence is checked against the quote it cites.
token-in-token-out (TITO) means the training pipeline consumes the exact tokenization and decoded-token stream produced by the inference engine, and uses it directly to build trajectories for learning— GLM-5: from Vibe Coding to Agentic Engineering
re-tokenization can introduce subtle mismatches in token boundaries, whitespace/normalization handling, truncation, or special-token placement— GLM-5: from Vibe Coding to Agentic Engineering
This ensures that token IDs are stable across multi-turn interactions, avoiding mismatches in the token ID representation of model outputs— laguna m1 xs2 technical report
it introduces the possibility of misalignment between the multi-turn trajectories produced by such a system and the chat template used for pro- duction deployments— laguna m1 xs2 technical report
Also called token-in-token-out, token-in, token-out (TITO) API design, Token-in-Token-out Gateway, Token-in-Token-out (TITO) gateway.
3 quotes from 2 sources, one card per model, each opening with its strongest.
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