MCTS论文趋势 2023–2026

主要结论

• MCTS论文从 2023 年的 115 篇增长到 2026 年的 278 篇，三年间扩大到约 2.4 倍。
• NeurIPS 是发MCTS论文最多的会议，2023–2026 年共 302 篇，占四个会议总量的 39%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 26 篇。
• 在「博弈与规划」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的经典规划是 3.3 倍，MCTS是 2.4 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 Regularization-Based Approach to Public Belief State Search for Adversarial Games
• ICML 2026$\alpha$-PFN: Fast Entropy Search via In-Context Learning
• ICLR 2026Better Learning-Augmented Spanning Tree Algorithms via Metric Forest Completion
• CVPR 2026DRS-GUI Dynamic Region Search for Training-Free GUI Grounding
• NeurIPS 2025A Single-Swap Local Search Algorithm for k-Means of Lines
• ICML 2025Accelerating Large Language Model Reasoning via Speculative Search
• ICLR 2025Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods
• CVPR 2025DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding
• NeurIPS 2024Speculative Monte-Carlo Tree Search
• ICML 2024Accelerated Speculative Sampling Based on Tree Monte Carlo
• ICLR 2024Chain of Log-Concave Markov Chains
• CVPR 2024Hierarchical Correlation Clustering and Tree Preserving Embedding
• NeurIPS 2023Accelerating Monte Carlo Tree Search with Probability Tree State Abstraction
• ICML 2023A new near-linear time algorithm for k-nearest neighbor search using a compressed cover tree
• ICLR 2023A GNN-Guided Predict-and-Search Framework for Mixed-Integer Linear Programming
• CVPR 2023Bridging Search Region Interaction With Template for RGB-T Tracking
• NeurIPS 2026A Revisit of Hamiltonian Monte Carlo Efficiency on Bayesian Neural Networks
• ICML 2026A Bi-metric Framework for Efficient Nearest Neighbor Search
• ICLR 2026Dr.LLM: Dynamic Layer Routing in LLMs
• CVPR 2026UAST Unified Active Search and Tracking for Arbitrary Targets with

全部MCTS论文

共 773 篇，第 3 / 16 页

101. ICML 2026Covariance estimation using Markov chain Monte Carlo
102. ICML 2026DC-LA: Difference-of-Convex Langevin Algorithm
103. ICML 2026Decision Tree Learning on Product Spaces
104. ICML 2026DiffuReason: Enhancing Reasoning Ability for Diffusion Language Models via Monte Carlo Tree Search
105. ICML 2026Diffusion Differentiable Resampling
106. ICML 2026Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence
107. ICML 2026Discrete Adjoint Schrödinger Bridge Sampler
108. ICML 2026DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching
109. ICML 2026Efficient Learning of Deep State Space Models via Importance Smoothing
110. ICML 2026Efficient Online Variational Estimation via Monte Carlo Sampling
111. ICML 2026Efficient Stochastic Optimisation via Sequential Monte Carlo
112. ICML 2026Entropic Mirror Monte Carlo
113. ICML 2026Escaping Whack-a-Mole: Optimizing Documentation as Repo-Specific Playbooks for Coding Agents
114. ICML 2026Exact and Approximate Algorithms for Polytree Learning
115. ICML 2026Excited Pfaffians: Generalized Neural Wave Functions Across Structure and State
116. ICML 2026Flatland: The Adventures of Gradient Descent with Large Step Sizes
117. ICML 2026Forward-KL Convergence of Time-Inhomogeneous Langevin Diffusions
118. ICML 2026From Rashomon Theory to PRAXIS: Efficient Decision Tree Rashomon Sets
119. ICML 2026Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime
120. ICML 2026Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback
121. ICML 2026Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior
122. ICML 2026InteractComp: Evaluating Search Agents With Ambiguous Queries
123. ICML 2026Inverting Data Transformations via Diffusion Sampling
124. ICML 2026Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo
125. ICML 2026Latent Guided Sampling for Combinatorial Optimization
126. ICML 2026LEAP: Zone-Aware MCTS for LLM Self-Speculative Decoding
127. ICML 2026Learning $U$-Statistics with Active Inference
128. ICML 2026Learning to Search and Searching to Learn for Generalization in Planning
129. ICML 2026Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models
130. ICML 2026Markov Chain Monte Carlo without Evaluating the Target: an Auxiliary Variable Approach
131. ICML 2026MARS: Modular Agent with Reflective Search for Automated AI Research
132. ICML 2026MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation
133. ICML 2026Matrix-Free GPU Semidefinite Programming for Quantum Ordered Search at the k=6 Frontier
134. ICML 2026MFH-NAS:A Hybrid Neural Architecture Search Framework for Multimodal Fusion Object Detection
135. ICML 2026MINT: Minimal Information Neuro-Symbolic Tree for Objective-Driven Knowledge-Gap Reasoning and Active Elicitation
136. ICML 2026Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling
137. ICML 2026Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis
138. ICML 2026Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models
139. ICML 2026Neural Low-Discrepancy Sequences
140. ICML 2026Neural Quantum States in Mixed Precision
141. ICML 2026Noisy Pairwise-Comparison Random Search for Smooth Nonconvex Optimization
142. ICML 2026NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search
143. ICML 2026OC-space: a Unifying Perspective on Verification of Tree Ensembles
144. ICML 2026On the Power of (Approximate) Reward Models for Inference-Time Scaling: Sequential Monte Carlo and Beyond
145. ICML 2026OneSearch: A Preliminary Exploration of the Unified End-to-End Generative Framework for E-commerce Search
146. ICML 2026Operator Splitting with Hamilton-Jacobi-based Proximals
147. ICML 2026Optimal Quantum Speedups for Repeatedly Nested Expectation Estimation
148. ICML 2026Path-dependent Discrete Amortized Inference
149. ICML 2026PINE: Pruning Boosted Tree Ensembles with Conformal In-Distribution Prediction Equivalence
150. ICML 2026Practical and Scalable Hamiltonian Monte Carlo Without the Metropolis Test

常见问题

2023–2026 年四大会议一共有多少篇MCTS论文？

共 773 篇，按年份分别是 2023 年 115 篇、2024 年 144 篇、2025 年 236 篇、2026 年 278 篇。

NeurIPS 2026 有多少篇MCTS论文？

NeurIPS 2026 有 99 篇MCTS论文，上一届是 100 篇。

ICLR 2026 有多少篇MCTS论文？

ICLR 2026 有 60 篇MCTS论文，上一届是 49 篇。

ICML 2026 有多少篇MCTS论文？

ICML 2026 有 105 篇MCTS论文，上一届是 75 篇。

CVPR 2026 有多少篇MCTS论文？

CVPR 2026 有 14 篇MCTS论文，上一届是 12 篇。

哪个会议的MCTS论文最多？

NeurIPS，2023–2026 年共 302 篇。