// ∞ Reasoning & Test-Time Compute
STaR (Self-Taught Reasoner)
Bootstraps reasoning by fine-tuning on the model's own correct rationales.
STaR 自举推理 2022 Intermediate core
IN PLAIN WORDS
Generate rationales, keep the ones with correct answers for fine-tuning, and rationalize failures given the answer. Iterating improves reasoning — an early self-improvement method.
Used in: Reasoning data synthesis
TIMELINE · prerequisites → this → what builds on it
01Original paper
STaR: Bootstrapping Reasoning With Reasoning
Eric Zelikman, Yuhuai Wu, Jesse Mu, et al. · 2022
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Then you can learn
- Nothing in the atlas builds on it yet
Related:RL with Verifiable Rewards (RLVR)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.
Explainers
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
star)