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 3,512 篇，第 52 / 71 页

  1. NeurIPS 2025RAST: Reasoning Activation in LLMs via Small-model Transfer
  2. NeurIPS 2025RBench-V: A Primary Assessment for Visual Reasoning Models with Multimodal Outputs
  3. NeurIPS 2025RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics
  4. NeurIPS 2025Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models
  5. NeurIPS 2025ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs
  6. NeurIPS 2025Reasoning as an Adaptive Defense for Safety
  7. NeurIPS 2025Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought
  8. NeurIPS 2025REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving
  9. NeurIPS 2025Reasoning Gym: Reasoning Environments for Reinforcement Learning with Verifiable Rewards
  10. NeurIPS 2025Reasoning Is Not a Race: When Stopping Early Beats Going Deeper
  11. NeurIPS 2025Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling
  12. NeurIPS 2025Reasoning Models Better Express Their Confidence
  13. NeurIPS 2025Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models
  14. NeurIPS 2025Reasoning Models Sometimes Output Illegible Chains of Thought
  15. NeurIPS 2025Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning
  16. NeurIPS 2025Reasoning Planning for Language Models
  17. NeurIPS 2025ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents
  18. NeurIPS 2025Redundancy-Aware Test-Time Graph Out-of-Distribution Detection
  19. NeurIPS 2025Reinforcement Learning for Reasoning in Large Language Models with One Training Example
  20. NeurIPS 2025Reinforcement Learning Teachers of Test Time Scaling
  21. NeurIPS 2025Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
  22. NeurIPS 2025Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models
  23. NeurIPS 2025Representation Consistency for Accurate and Coherent LLM Answer Aggregation
  24. NeurIPS 2025Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition
  25. NeurIPS 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
  26. NeurIPS 2025ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
  27. NeurIPS 2025Restricted Spectral Gap Decomposition for Simulated Tempering Targeting Mixture Distributions
  28. NeurIPS 2025Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning
  29. NeurIPS 2025Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling
  30. NeurIPS 2025Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
  31. NeurIPS 2025Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models
  32. NeurIPS 2025Reward Reasoning Models
  33. NeurIPS 2025RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility
  34. NeurIPS 2025Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI
  35. NeurIPS 2025Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization
  36. NeurIPS 2025RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
  37. NeurIPS 2025RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
  38. NeurIPS 2025Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
  39. NeurIPS 2025Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods
  40. NeurIPS 2025ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks
  41. NeurIPS 2025RrED: Black-box Unsupervised Domain Adaptation via Rectifying-reasoning Errors of Diffusion
  42. NeurIPS 2025rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset
  43. NeurIPS 2025RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video
  44. NeurIPS 2025S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models
  45. NeurIPS 2025SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment
  46. NeurIPS 2025SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning
  47. NeurIPS 2025Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
  48. NeurIPS 2025SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning
  49. NeurIPS 2025Scalable Best-of-N Selection for Large Language Models via Self-Certainty
  50. NeurIPS 2025Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning

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