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 500 篇，第 7 / 10 页

  1. NeurIPS 2025Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning
  2. NeurIPS 2025PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts
  3. NeurIPS 2025Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning
  4. NeurIPS 2025Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning
  5. NeurIPS 2025Privacy Reasoning in Ambiguous Contexts
  6. NeurIPS 2025Probabilistic Reasoning with LLMs for Privacy Risk Estimation
  7. NeurIPS 2025Prompting as Scientific Inquiry
  8. NeurIPS 2025ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
  9. NeurIPS 2025ProtoPairNet: Interpretable Regression through Prototypical Pair Reasoning
  10. NeurIPS 2025Provable Scaling Laws for the Test-Time Compute of Large Language Models
  11. NeurIPS 2025PSI: A Benchmark for Human Interpretation and Response in Traffic Interactions
  12. NeurIPS 2025PurpCode: Reasoning for Safer Code Generation
  13. NeurIPS 2025QFFT, Question-Free Fine-Tuning for Adaptive Reasoning
  14. NeurIPS 2025Quantifying Elicitation of Latent Capabilities in Language Models
  15. NeurIPS 2025QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?
  16. NeurIPS 2025R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
  17. NeurIPS 2025R1-ShareVL: Incentivizing Reasoning Capabilities of Multimodal Large Language Models via Share-GRPO
  18. NeurIPS 2025R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
  19. NeurIPS 2025RADAR: Benchmarking Language Models on Imperfect Tabular Data
  20. NeurIPS 2025RAST: Reasoning Activation in LLMs via Small-model Transfer
  21. NeurIPS 2025RBench-V: A Primary Assessment for Visual Reasoning Models with Multimodal Outputs
  22. NeurIPS 2025RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics
  23. NeurIPS 2025Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models
  24. NeurIPS 2025ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs
  25. NeurIPS 2025Reasoning as an Adaptive Defense for Safety
  26. NeurIPS 2025Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought
  27. NeurIPS 2025REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving
  28. NeurIPS 2025Reasoning Gym: Reasoning Environments for Reinforcement Learning with Verifiable Rewards
  29. NeurIPS 2025Reasoning Is Not a Race: When Stopping Early Beats Going Deeper
  30. NeurIPS 2025Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling
  31. NeurIPS 2025Reasoning Models Better Express Their Confidence
  32. NeurIPS 2025Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models
  33. NeurIPS 2025Reasoning Models Sometimes Output Illegible Chains of Thought
  34. NeurIPS 2025Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning
  35. NeurIPS 2025Reasoning Planning for Language Models
  36. NeurIPS 2025ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents
  37. NeurIPS 2025Redundancy-Aware Test-Time Graph Out-of-Distribution Detection
  38. NeurIPS 2025Reinforcement Learning for Reasoning in Large Language Models with One Training Example
  39. NeurIPS 2025Reinforcement Learning Teachers of Test Time Scaling
  40. NeurIPS 2025Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
  41. NeurIPS 2025Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models
  42. NeurIPS 2025Representation Consistency for Accurate and Coherent LLM Answer Aggregation
  43. NeurIPS 2025Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition
  44. NeurIPS 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
  45. NeurIPS 2025ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
  46. NeurIPS 2025Restricted Spectral Gap Decomposition for Simulated Tempering Targeting Mixture Distributions
  47. NeurIPS 2025Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning
  48. NeurIPS 2025Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling
  49. NeurIPS 2025Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
  50. NeurIPS 2025Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models

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