About this paper
A hybrid decision model routes between implicit single-forward-pass answering and full autoregressive reasoning via a self-routing block trained with calibrated decision policy optimization, reducing token and latency costs while preserving accuracy.
Existing adaptive-reasoning methods shorten the explicit reasoning a model writes, or skip it by switching modes; either way the answer is still written out token by token. Rather than deciding how much to think, we explore a different paradigm, zero-or-T thinking: a single model either answers from the implicit thinking inside one forward pass, generating no token, or performs full autoregressive reasoning at a cost of T tokens when that is worth paying. We realise it in a hybrid decision model (HDM), where one frozen backbone serves both modes and a lightweight self-routing block chooses between them. The block estimates the value of thinking, the utility the slow mode is expected to add…
adaptive-reasoningexplicit reasoningimplicit thinkingzero-or-T thinkinghybrid decision modelfrozen backboneself-routing blockvalue of thinkingautoregressive reasoningforward pass
- Upvotes
- 4
- Authors
- 6
- Published
- Nov 12, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
The Value of Thinking: Learning When to Reason in Hybrid Decision Models was first seen on Hugging Face · Daily papers on Nov 14, 2026. Since then it has appeared in 16 checks on 3 different days. Its best position was #21 of 30, reached on Nov 16, 03:28 UTC. It is #25 right now, slipping from #22 to #25 over the last 6 checks.