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 236 篇，第 2 / 5 页

51. ICLR 2025Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search
52. ICLR 2025Strength Estimation and Human-Like Strength Adjustment in Games
53. ICLR 2025SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement
54. ICLR 2025Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo
55. ICLR 2025Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search
56. ICLR 2025Test-time Alignment of Diffusion Models without Reward Over-optimization
57. ICLR 2025Tree of Attributes Prompt Learning for Vision-Language Models
58. ICLR 2025Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search
59. ICLR 2025Unsupervised Model Tree Heritage Recovery
60. ICLR 2025Variance-Reducing Couplings for Random Features
61. ICLR 2025Variational Search Distributions
62. ICML 2025A General Framework for Inference-time Scaling and Steering of Diffusion Models
63. ICML 2025A Mixture-Based Framework for Guiding Diffusion Models
64. ICML 2025A Physics-Augmented Deep Learning Framework for Classifying Single Molecule Force Spectroscopy Data
65. ICML 2025A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic Approach
66. ICML 2025A Unified Framework for Entropy Search and Expected Improvement in Bayesian Optimization
67. ICML 2025Accelerating Large Language Model Reasoning via Speculative Search
68. ICML 2025Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching
69. ICML 2025Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search
70. ICML 2025Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
71. ICML 2025AutoAL: Automated Active Learning with Differentiable Query Strategy Search
72. ICML 2025AutoStep: Locally adaptive involutive MCMC
73. ICML 2025BARK: A Fully Bayesian Tree Kernel for Black-box Optimization
74. ICML 2025Beyond Communication Overhead: A Multilevel Monte Carlo Approach for Mitigating Compression Bias in Distributed Learning
75. ICML 2025Branches: Efficiently Seeking Optimal Sparse Decision Trees via AO*
76. ICML 2025Can We Predict Performance of Large Models across Vision-Language Tasks?
77. ICML 2025CombiMOTS: Combinatorial Multi-Objective Tree Search for Dual-Target Molecule Generation
78. ICML 2025Complete-Tree Space Favors Data-Efficient Link Prediction
79. ICML 2025Conditioning Diffusions Using Malliavin Calculus
80. ICML 2025Deep Electromagnetic Structure Design Under Limited Evaluation Budgets
81. ICML 2025Diagonal Symmetrization of Neural Network Solvers for the Many-Electron Schrödinger Equation
82. ICML 2025Differential Privacy Guarantees of Markov Chain Monte Carlo Algorithms
83. ICML 2025Efficient Noise Calculation in Deep Learning-based MRI Reconstructions
84. ICML 2025Efficiently Vectorized MCMC on Modern Accelerators
85. ICML 2025EGPlace: An Efficient Macro Placement Method via Evolutionary Search with Greedy Repositioning Guided Mutation
86. ICML 2025Ehrenfeucht-Haussler Rank and Chain of Thought
87. ICML 2025Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems
88. ICML 2025EvoPress: Accurate Dynamic Model Compression via Evolutionary Search
89. ICML 2025Feasible Action Search for Bandit Linear Programs via Thompson Sampling
90. ICML 2025Graph-Based Algorithms for Diverse Similarity Search
91. ICML 2025Importance Corrected Neural JKO Sampling
92. ICML 2025Improving Consistency Models with Generator-Augmented Flows
93. ICML 2025Inverse Problem Sampling in Latent Space Using Sequential Monte Carlo
94. ICML 2025KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search
95. ICML 2025Language Models as Implicit Tree Search
96. ICML 2025Large Language Model-driven Large Neighborhood Search for Large-Scale MILP Problems
97. ICML 2025Learning Extrapolative Sequence Transformations from Markov Chains
98. ICML 2025Linear Mode Connectivity between Multiple Models modulo Permutation Symmetries
99. ICML 2025Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space
100. ICML 2025Mastering Board Games by External and Internal Planning with Language Models

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。