跳到正文- Test-Time Compute
- Source: Understanding R1-Zero-Like Training (Dr. GRPO)
- Source: Tulu 3 (Lambert et al., 2024) — RLVR
- Source: Tree of Thoughts: Deliberate Problem Solving with Large Language Models
- Source: The "think" tool (Anthropic Engineering, 2025)
- Source: STaR — Self-Taught Reasoner (Zelikman et al., 2022)
- Source: Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Source: Scaling LLM Test-Time Compute Optimally (Snell et al., 2024)
- Source: s1 — Simple Test-Time Scaling (Muennighoff et al., 2025)
- Source: ReWOO: Decoupling Reasoning from Observations (Xu et al., 2023)
- Source: Reflexion: Language Agents with Verbal Reinforcement Learning (Shinn et al., 2023)
- Source: Reasoning models guide (OpenAI API docs)
- Source: Reasoning models don't always say what they think (Anthropic)
- Source: Reasoning best practices (OpenAI)
- Source: ReAct: Synergizing Reasoning and Acting in Language Models (Yao et al., 2022)
- Source: Prompting Science Report 2: The Decreasing Value of Chain of Thought
- Source: On the Brittle Foundations of ReAct Prompting for Agentic LLMs (Verma et al., 2024)
- Source: Notebook experiment 17-tree-of-thoughts (Tree of Thoughts)
- Source: Notebook experiment 16-self-consistency (Self-Consistency)
- Source: Notebook experiment 15-chain-of-thought (Chain-of-Thought)
- Source: Learning to Reason with LLMs (OpenAI, 2024)
- Source: Large Language Models are Zero-Shot Reasoners
- Source: Language Models Don't Always Say What They Think
- Source: Language Agent Tree Search (LATS, Zhou et al., 2023)
- Source: Inverse Scaling in Test-Time Compute (Gema et al., 2025)
- Source: Gemini API Docs — Thinking
- Source: Does RL Really Incentivize Reasoning Beyond the Base Model? (Yue et al., 2025)
- Source: Do NOT Think That Much for 2+3=? (Chen et al., 2024)
- Source: DeepSeek-R1 (DeepSeek-AI, 2025)
- Source: DeepSeek API Docs — Thinking Mode
- Source: DAPO (Yu et al., 2025)
- Source: Claude's Extended Thinking (Anthropic, 2025)
- Source: Claude API Docs — Thinking
- Source: Claude API Docs — Steering Thinking
- Source: Claude API Docs — Extended Thinking (manual budget)
- Source: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Reinforcement Fine-Tuning
- Reasoning Models
- ReAct pattern
- Extended Thinking
- Chain-of-thought