// ∞ Reasoning & Test-Time Compute

Budget Forcing (s1)

Controls test-time compute by forcing thinking to extend or stop.

预算强制（s1） 2025 Intermediate extended

IN PLAIN WORDS

Fine-tune on 1,000 curated reasoning traces, then append “Wait” when the model tries to stop, or cut it off at budget — a minimal demo of test-time scaling.

Used in: Reasoning research baseline

TIMELINE · prerequisites → this → what builds on it

2024 Test-Time Com…2025 Budget Forcing (s…

01Original paper

s1: Simple test-time scaling

Niklas Muennighoff, Zitong Yang, Weijia Shi, et al. · 2025

arXiv ↗ ✓ Verified · arXiv API

02Where it sits

Learn the left column first; the right column builds on this one.

Learn first

Test-Time Compute Scaling

Budget Forcing (s1)

Then you can learn

Nothing in the atlas builds on it yet

Related:DeepSeek-R1 Reasoning RL Recipe

Left: prerequisites · right: builds on this · dashed: related. Full map →

03Learning resources

Official docs, explainers, courses and reference code. All links checked.

Reference code

github.com ↗EN

04Where the course teaches it

U52 Reasoning Models: RLVR, GRPO & Test-Time Compute Chain of thought, self-consistency, process rewards, GRPO/DAPO, verifiable rewards and the R1 recipe. 12 h12 algorithms5 papers

For AI / data

Verification: verified, checked 2026-10-21.
JSON: /api/learn/algorithms.json (id: budget-forcing)