Inference-time reasoning

英文原文文件：inference_time_reasoning.md

计算解释

在预训练后通过提示与采样策略投入额外推理阶段计算，而非修改模型权重的方法。

支撑阅读卡

• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models (2022, inference_time_compute_post_training)
• ReAct: Synergizing Reasoning and Acting in Language Models (2022, inference_time_compute_post_training)
• Self-Consistency Improves Chain of Thought Reasoning in Language Models (2022, inference_time_compute_post_training)
• Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks (2022, inference_time_compute_post_training)
• Let's Verify Step by Step (2023, inference_time_compute_post_training)
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models (2023, inference_time_compute_post_training)
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning (2025, inference_time_compute_post_training)
• Kimi k1.5: Scaling Reinforcement Learning with LLMs (2025, inference_time_compute_post_training)
• s1: Simple test-time scaling (2025, inference_time_compute_post_training)
• Qwen3 Technical Report (2025, hyperscale_dense_llm_training)
• Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2 (2025, search_simulation_science_compute)
• AlphaEvolve: A coding agent for scientific and algorithmic discovery (2025, search_simulation_science_compute)
• DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models (2025, sparse_memory_efficient_scaling)
• Kimi K2.5: Visual Agentic Intelligence (2026, inference_time_compute_post_training)

后续计算范式下过时或退居次要的内容

仅通过已链接的阅读卡追踪，不将本方法页视为独立证据来源。