The Value of Thinking: Learning When to Reason in Hybrid Decision Models
Abstract
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 over the fast one, from what that implicit thinking has already produced, and the slow mode runs only where that value exceeds a price λ set per request. Where no per-decision label exists, as in episodic agentic tasks, we introduce Calibrated Decision Policy Optimisation (CDPO), a reinforcement-learning recipe that trains the block from episode-level returns. We evaluate HDM on MMLU-Pro, AGIEval, GPQA-Diamond, JevBench, BANKING77 and MiniWoB. Specifically, on JevBench HDM-4B scores 0.857 against Jev's 0.851 (+0.7%) at a median 0.179\,s against 0.652 (-72.5%). On the agentic venue MiniWoB HDM-27B cuts token cost by 80.1%.
Community
HDM, a hybrid decision model: one that decides for itself whether an answer needs autoregressive generation at all, so a question costs either no token or a full reasoning pass.
Letting the model answer from one forward pass and only paying for T tokens when the value of thinking exceeds a price is a clean way to frame it. Pricing it per request with lambda is the bit I like. How stable is the router when the price changes at test time without retraining?
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- ThinkJev: One Thought, Every Budget for Calibrated Typed Decisions (2026)
- LEV: Thinking Fast and Deep with Looped Decision Models (2026)
- What Can't Jev Decide? Probing the Limits of One-Pass Decision Models (2026)
- SanSi: A Looped Typed Decision Model for System 1.5 Thinking (2026)
- System1-Arena: Which Decisions Can Be Left to System 1? (2026)
- DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning (2026)
- Truncated Reasoning Under a Budget: Evaluating System-1 Models as Decision-Makers (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Deciding when thinking is worth paying for is an estimator's problem. You don't do a full takeoff on every lead. You glance, and only the jobs that might pay off get the long look. Setting the price per request is a nice touch. I'd be curious how often the quick answer was wrong on cases the router skipped.
Get this paper in your agent:
hf papers read 2611.16961 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper