推理模型论文趋势 2023–2026

链式推理、测试时计算与显式推理能力

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 3,512 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

推理模型论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20232715710933470
2024121846343311
202550020315970932
20263616525822041,799

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部推理模型论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 932 篇，第 17 / 19 页

  1. NeurIPS 2025Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning
  2. NeurIPS 2025Scaling Physical Reasoning with the PHYSICS Dataset
  3. NeurIPS 2025Scaling RL to Long Videos
  4. NeurIPS 2025Scaling Speculative Decoding with Lookahead Reasoning
  5. NeurIPS 2025Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
  6. NeurIPS 2025SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning
  7. NeurIPS 2025Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging
  8. NeurIPS 2025SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought
  9. NeurIPS 2025scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery
  10. NeurIPS 2025SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models
  11. NeurIPS 2025SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
  12. NeurIPS 2025Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning
  13. NeurIPS 2025Searching Latent Program Spaces
  14. NeurIPS 2025SeePhys: Does Seeing Help Thinking? – Benchmarking Vision-Based Physics Reasoning
  15. NeurIPS 2025Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
  16. NeurIPS 2025Self-Verifying Reflection Helps Transformers with CoT Reasoning
  17. NeurIPS 2025SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens
  18. NeurIPS 2025Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning
  19. NeurIPS 2025Sherlock: Self-Correcting Reasoning in Vision-Language Models
  20. NeurIPS 2025ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning
  21. NeurIPS 2025SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation
  22. NeurIPS 2025Simulating Society Requires Simulating Thought
  23. NeurIPS 2025Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models
  24. NeurIPS 2025SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
  25. NeurIPS 2025Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families
  26. NeurIPS 2025SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
  27. NeurIPS 2025Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
  28. NeurIPS 2025SolidGeo: Measuring Multimodal Spatial Math Reasoning in Solid Geometry
  29. NeurIPS 2025SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search
  30. NeurIPS 2025Solving Inequality Proofs with Large Language Models
  31. NeurIPS 2025SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement
  32. NeurIPS 2025SPACE: SPike-Aware Consistency Enhancement for Test-Time Adaptation in Spiking Neural Networks
  33. NeurIPS 2025Sparse Diffusion Autoencoder for Test-time Adapting Prediction of Complex Systems
  34. NeurIPS 2025SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning
  35. NeurIPS 2025SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning
  36. NeurIPS 2025SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
  37. NeurIPS 2025SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models
  38. NeurIPS 2025SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning
  39. NeurIPS 2025SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning
  40. NeurIPS 2025Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning
  41. NeurIPS 2025StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs
  42. NeurIPS 2025STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization
  43. NeurIPS 2025Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs
  44. NeurIPS 2025Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
  45. NeurIPS 2025SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
  46. NeurIPS 2025SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications
  47. NeurIPS 2025SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning
  48. NeurIPS 2025SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
  49. NeurIPS 2025System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts
  50. NeurIPS 2025T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查推理模型在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "reasoning-models"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇推理模型论文？
共 3,512 篇，按年份分别是 2023 年 470 篇、2024 年 311 篇、2025 年 932 篇、2026 年 1,799 篇。
NeurIPS 2026 有多少篇推理模型论文？
NeurIPS 2026 有 361 篇推理模型论文，上一届是 500 篇。
ICLR 2026 有多少篇推理模型论文？
ICLR 2026 有 652 篇推理模型论文，上一届是 203 篇。
ICML 2026 有多少篇推理模型论文？
ICML 2026 有 582 篇推理模型论文，上一届是 159 篇。
CVPR 2026 有多少篇推理模型论文？
CVPR 2026 有 204 篇推理模型论文，上一届是 70 篇。
哪个会议的推理模型论文最多？
NeurIPS，2023–2026 年共 1,253 篇。

「前沿系统」下的其他主题