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 10 / 19 页

  1. NeurIPS 2025Activation-Guided Consensus Merging for Large Language Models
  2. NeurIPS 2025Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization
  3. NeurIPS 2025Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
  4. NeurIPS 2025AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking
  5. NeurIPS 2025AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners
  6. NeurIPS 2025AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models
  7. NeurIPS 2025AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents
  8. NeurIPS 2025AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks
  9. NeurIPS 2025Analog Foundation Models
  10. NeurIPS 2025Analyzing the Power of Chain of Thought through Memorization Capabilities
  11. NeurIPS 2025Anchored Diffusion Language Model
  12. NeurIPS 2025AnomalyCoT: A Multi-Scenario Chain-of-Thought Dataset for Multimodal Large Language Models
  13. NeurIPS 2025Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector
  14. NeurIPS 2025APOLLO: Automated LLM and Lean Collaboration for Advanced Formal Reasoning
  15. NeurIPS 2025Are Language Models Efficient Reasoners? A Perspective from Logic Programming
  16. NeurIPS 2025Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost
  17. NeurIPS 2025ARM: Adaptive Reasoning Model
  18. NeurIPS 2025AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Science
  19. NeurIPS 2025Atom of Thoughts for Markov LLM Test-Time Scaling
  20. NeurIPS 2025Atomic Thinking of LLMs: Decoupling and Exploring Mathematical Reasoning Abilities
  21. NeurIPS 2025Attention (as Discrete-Time Markov) Chains
  22. NeurIPS 2025Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings
  23. NeurIPS 2025Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
  24. NeurIPS 2025Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models
  25. NeurIPS 2025AudSemThinker: Enhancing Audio-Language Models Through Reasoning over Semantics of Sound
  26. NeurIPS 2025Automated Model Discovery via Multi-modal & Multi-step Pipeline
  27. NeurIPS 2025AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling
  28. NeurIPS 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
  29. NeurIPS 2025Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation
  30. NeurIPS 2025BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
  31. NeurIPS 2025Bag of Tricks for Inference-time Computation of LLM Reasoning
  32. NeurIPS 2025Benchmarking Large Language Models with Integer Sequence Generation Tasks
  33. NeurIPS 2025Benchmarking Spatiotemporal Reasoning in LLMs and Reasoning Models: Capabilities and Challenges
  34. NeurIPS 2025Best-of-N Jailbreaking
  35. NeurIPS 2025Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations
  36. NeurIPS 2025Beyond Oracle: Verifier-Supervision for Instruction Hierarchy in Reasoning and Instruction-Tuned LLMs
  37. NeurIPS 2025Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs
  38. NeurIPS 2025Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
  39. NeurIPS 2025Beyond Verifiable Rewards: Scaling Reinforcement Learning in Language Models to Unverifiable Data
  40. NeurIPS 2025BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model
  41. NeurIPS 2025BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception
  42. NeurIPS 2025BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset
  43. NeurIPS 2025Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation
  44. NeurIPS 2025BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning
  45. NeurIPS 2025BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent
  46. NeurIPS 2025Buffer layers for Test-Time Adaptation
  47. NeurIPS 2025C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning
  48. NeurIPS 2025CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward
  49. NeurIPS 2025CALM: Culturally Self-Aware Language Models
  50. NeurIPS 2025Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs

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