CIRF: Tokenizing Chain-of-Thoughts into Reusable Functional Units for Efficient Latent Reasoning in Large Language Models
Replaces written reasoning steps with reusable discrete tokens learned from their functional roles. The model generates these tokens with optional short textual results before answering, and prunes textual results according to their effect on answer prediction.
First public: · Added to this list: November 2, 2026
Explore this approach
Thinking tokens — Give a model extra tokens for computation, such as pauses, filler symbols, or learned planning tokens. These tokens need not spell out the solution.
Internalized reasoning — Learn from worked solutions so that some or all of the reasoning can later happen without writing those steps. Training may use a separate teacher model or progressively remove written steps from the model being trained.