Trendoday

The Value of Thinking: Learning When to Reason in Hybrid Decision Models

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 mu

  • Upvotes4
#25Rank now 4
#21Peak rank
3Days on list
96Score · 7d
Nov 14, 2026First seen
Rank · 7 days

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.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 23:2806:5814:2821:5805:28 Nov 14, 23:28 UTC · #28Nov 15, 01:28 UTC · #29Nov 15, 03:28 UTC · #29Nov 15, 05:28 UTC · #29Nov 15, 07:28 UTC · #27Nov 15, 09:28 UTC · #24Nov 15, 11:28 UTC · #22Nov 15, 13:28 UTC · #22Nov 15, 15:28 UTC · #22Nov 15, 17:28 UTC · #22Nov 15, 19:28 UTC · #22Nov 15, 21:28 UTC · #22Nov 15, 23:28 UTC · #23Nov 16, 01:28 UTC · #23Nov 16, 03:28 UTC · #21Nov 16, 05:28 UTC · #25

Last 14 days

Best rank per day (UTC).

Nov 3today

Metric history

▲ as reported by Hugging Face.

0257 23:2806:5814:2821:5805:28 Nov 14, 23:28 UTC · 4Nov 15, 01:28 UTC · 4Nov 15, 03:28 UTC · 4Nov 15, 05:28 UTC · 4Nov 15, 07:28 UTC · 5Nov 15, 09:28 UTC · 6Nov 15, 11:28 UTC · 7Nov 15, 13:28 UTC · 7Nov 15, 15:28 UTC · 7Nov 15, 17:28 UTC · 7Nov 15, 19:28 UTC · 7Nov 15, 21:28 UTC · 7Nov 15, 23:28 UTC · 7Nov 16, 01:28 UTC · 7Nov 16, 03:28 UTC · 7Nov 16, 05:28 UTC · 7

Questions

Is The Value of Thinking: Learning When to Reason in Hybrid Decision Models trending on HF Daily Papers right now?

Yes. As of Nov 16, 05:28 UTC it is #25, slipping from #22 to #25 over the last 6 checks.

What is the highest rank The Value of Thinking: Learning When to Reason in Hybrid Decision Models reached?

#21 on Hugging Face · Daily papers, on Nov 16, 03:28 UTC. Trendoday checks this list every 120 minutes.

How long has The Value of Thinking: Learning When to Reason in Hybrid Decision Models been trending?

It was first seen on Nov 14, 2026 and has been on the list on 3 days (16 checks) since.