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 26 / 71 页

  1. ICML 2026Reasoning-VLA: An Efficient and Spatial-Guided General Vision-Language-Action Reasoning Model for Autonomous Driving
  2. ICML 2026Recursive Binding on a Budget: Subspace Carving in Order-$p$ Tensor Memories
  3. ICML 2026RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache Reuse
  4. ICML 2026Reflector: Internalizing Step-wise Reflection against Indirect Jailbreaks
  5. ICML 2026Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
  6. ICML 2026Reinforcement-aware Knowledge Distillation for LLM Reasoning
  7. ICML 2026ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning
  8. ICML 2026Reliable Thinking with Images
  9. ICML 2026rePIRL: Learn PRM with Inverse RL for LLM Reasoning
  10. ICML 2026ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware Training
  11. ICML 2026ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards
  12. ICML 2026Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models
  13. ICML 2026Rethinking Instruction Drift as a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planning
  14. ICML 2026Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective
  15. ICML 2026RL with Learnable Textual Feedback: A Bilevel Approach
  16. ICML 2026RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments
  17. ICML 2026Routing and Reasoned Evaluation with Large Language Models
  18. ICML 2026SafeCompass: Dynamic Chain-of-Thought Steering via Inference-Time Safety Signals
  19. ICML 2026Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away
  20. ICML 2026SaTeen: Learning Structural Alignment for Continual Test-Time Adaptation
  21. ICML 2026Scaling Generative Verifiers For Natural Language Mathematical Proof Verification And Selection
  22. ICML 2026Scaling Inference-Time Computation via Opponent Simulation: Enabling Online Strategic Adaptation in Repeated Negotiation
  23. ICML 2026Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning
  24. ICML 2026Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers
  25. ICML 2026Scaling-Aware Adapter for Structure-Grounded LLM Reasoning
  26. ICML 2026Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models
  27. ICML 2026Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models
  28. ICML 2026Scientific logicality enriched methodology for LLM reasoning: A practice in physics
  29. ICML 2026Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories
  30. ICML 2026Seeing is Solving: Unlocking Efficient Multimodal RL via View Alignment
  31. ICML 2026Seeing Without Understanding: Disentangling Perception, Reasoning, and Simulation in VLM Gameplay
  32. ICML 2026Seg-ReSearch: Segmentation with Interleaved Reasoning and External Search
  33. ICML 2026Segment-Aligned Policy Optimization for Multi-Modal Reasoning
  34. ICML 2026Select to Think: Unlocking SLM Potential with Local Sufficiency
  35. ICML 2026Self-correcting for Debiasing Large Language Models
  36. ICML 2026Self-CriTeach: LLM Self-Teaching and Self-Critiquing for Improving Robotic Planning via Automated Domain Generation
  37. ICML 2026Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression
  38. ICML 2026Semantic-Enriched Latent Visual Reasoning
  39. ICML 2026Semi-knockoffs: a model-agnostic conditional independence testing method with finite-sample guarantees
  40. ICML 2026SemRep : Generative Code Representation Learning with Code Transformations
  41. ICML 2026Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery
  42. ICML 2026Shape of Thought: Progressive Object Assembly via Visual Chain-of-Thought
  43. ICML 2026Short Chains, Deep Thoughts: Balancing Reasoning Efficiency and Intra-Segment Capability via Split-Merge Optimization
  44. ICML 2026Show, Don't Tell: Morphing Latent Reasoning into Image Generation
  45. ICML 2026Shrinking the Variance: Shrinkage Baselines for Reinforcement Learning with Verifiable Rewards
  46. ICML 2026Simple Policy Gradients for Reasoning with Diffusion Language Models
  47. ICML 2026SL-VC: A Benchmark and Automated Framework for Separation Logic Verification Condition Proving
  48. ICML 2026SLASH the Sink: Sharpening Structural Attention Inside LLMs
  49. ICML 2026SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning
  50. ICML 2026SLQ: Bridging Modalities via Shared Latent Queries for Retrieval with Frozen MLLMs

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