推理模型论文趋势 2023–2026

主要结论

• 推理模型论文从 2023 年的 470 篇增长到 2026 年的 1,799 篇，三年间扩大到约 3.8 倍。
• NeurIPS 是发推理模型论文最多的会议，2023–2026 年共 1,253 篇，占四个会议总量的 36%。
• 交叉方向里涨得最快的是强化学习：同时属于两个主题的论文从 2023 年的 9 篇增至 2026 年的 437 篇。
• 在「前沿系统」的 4 个主题里，它的 2026 年论文数排第 3；同组增长最快的AI 智能体是 12 倍，推理模型是 3.8 倍。

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

• NeurIPS 2026A Mechanistic Analysis of Looped Reasoning Language Models
• ICML 2026A Formal Comparison Between Chain of Thought and Latent Thought
• ICLR 2026A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models
• CVPR 2026Asking like Socrates Socrates helps VLMs understand remote sensing images
• NeurIPS 2025A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
• ICML 2025A Reasoning-Based Approach to Cryptic Crossword Clue Solving
• ICLR 2025A Formal Framework for Understanding Length Generalization in Transformers
• CVPR 2025Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought
• NeurIPS 2024Are Large Language Models Good Statisticians?
• ICML 2024Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
• ICLR 2024Amortizing intractable inference in large language models
• CVPR 2024Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts
• NeurIPS 2023A benchmark of categorical encoders for binary classification
• ICML 2023Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?
• ICLR 2023Automatic Chain of Thought Prompting in Large Language Models
• CVPR 2023ActMAD: Activation Matching To Align Distributions for Test-Time-Training
• NeurIPS 2026A Solvable Model of Chain-of-Thought in In-Context Learning
• ICML 2026A Narrowing Geometry in Contaminated Reasoning
• ICLR 2026A State-Transition Framework for Efficient LLM Reasoning
• CVPR 2026Beyond Weak Supervision MLLMs-Guided Graded Knowledge Distillation for Unsupervised Camouflaged

全部推理模型论文

共 1,253 篇，第 16 / 26 页

751. NeurIPS 2025Simulating Society Requires Simulating Thought
752. NeurIPS 2025Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models
753. NeurIPS 2025SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
754. NeurIPS 2025Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families
755. NeurIPS 2025SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
756. NeurIPS 2025Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
757. NeurIPS 2025SolidGeo: Measuring Multimodal Spatial Math Reasoning in Solid Geometry
758. NeurIPS 2025SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search
759. NeurIPS 2025Solving Inequality Proofs with Large Language Models
760. NeurIPS 2025SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement
761. NeurIPS 2025SPACE: SPike-Aware Consistency Enhancement for Test-Time Adaptation in Spiking Neural Networks
762. NeurIPS 2025Sparse Diffusion Autoencoder for Test-time Adapting Prediction of Complex Systems
763. NeurIPS 2025SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning
764. NeurIPS 2025SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning
765. NeurIPS 2025SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
766. NeurIPS 2025SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models
767. NeurIPS 2025SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning
768. NeurIPS 2025SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning
769. NeurIPS 2025Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning
770. NeurIPS 2025StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs
771. NeurIPS 2025STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization
772. NeurIPS 2025Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs
773. NeurIPS 2025Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
774. NeurIPS 2025SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
775. NeurIPS 2025SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications
776. NeurIPS 2025SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning
777. NeurIPS 2025SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
778. NeurIPS 2025System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts
779. NeurIPS 2025T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
780. NeurIPS 2025Table as a Modality for Large Language Models
781. NeurIPS 2025TCM-Ladder: A Benchmark for Multimodal Question Answering on Traditional Chinese Medicine
782. NeurIPS 2025Teaching Language Models to Reason with Tools
783. NeurIPS 2025TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs
784. NeurIPS 2025Test-Time Adaptation by Causal Trimming
785. NeurIPS 2025The Dual Nature of Plasticity Loss in Deep Continual Learning: Dissection and Mitigation
786. NeurIPS 2025The Emergence of Abstract Thought in Large Language Models Beyond Any Language
787. NeurIPS 2025The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
788. NeurIPS 2025The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness
789. NeurIPS 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
790. NeurIPS 2025The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training
791. NeurIPS 2025The Promise of RL for Autoregressive Image Editing
792. NeurIPS 2025The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning
793. NeurIPS 2025Think Only When You Need with Large Hybrid-Reasoning Models
794. NeurIPS 2025Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens
795. NeurIPS 2025Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
796. NeurIPS 2025Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
797. NeurIPS 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
798. NeurIPS 2025ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning
799. NeurIPS 2025Thinker: Learning to Think Fast and Slow
800. NeurIPS 2025Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning

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。