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 99 篇，第 2 / 2 页

51. NeurIPS 2026Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again
52. NeurIPS 2026On Worst-Case Guarantees for Graph-Based Nearest-Neighbor Search
53. NeurIPS 2026OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework
54. NeurIPS 2026OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
55. NeurIPS 2026Order-Marginalized Scoring for Masked Diffusion Models
56. NeurIPS 2026Ordinary Least Squares as an Attention Mechanism
57. NeurIPS 2026PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
58. NeurIPS 2026PE-SHAP: Causally Interpretable Path-Wise Shapley Explanations
59. NeurIPS 2026PiCA: Pivot-Based Credit Assignment For Search Agentic Reinforcement Learning
60. NeurIPS 2026QUEST: Q-Learning for Uncertainty-Guided Efficient Search Teams
61. NeurIPS 2026Random-Projection Tree Stein Variational Gradient Descent
62. NeurIPS 2026Recovering the Apresjan Hierarchy Using Linkage-Based Clustering
63. NeurIPS 2026Regularized Large Neighborhood Search
64. NeurIPS 2026Resolving Time-Frequency Ridge Crossings via Frequency-Rate Lifting
65. NeurIPS 2026Retriever-Free Retrieval-Augmented Reasoning via Corpus-Traversing MCTS
66. NeurIPS 2026Robust Approximate Nearest Neighbor Search for Any Dataset
67. NeurIPS 2026Runtime Analysis of Cartesian Genetic Programming on MAX: A Proven Exponential Speedup
68. NeurIPS 2026ScaleBITS: Scalable Bitwidth Search for Hardware-Aligned Mixed-Precision LLMs
69. NeurIPS 2026SCOUT: Planning under Occlusion via Object-Centric World Model Rollouts
70. NeurIPS 2026SD-Search: Hindsight Self-Distillation for Search-Augmented Reasoning
71. NeurIPS 2026Search at the Cost of Sampling: Nearly-Instant Latent Space Bayesian Optimization
72. NeurIPS 2026SEEK-VAU: Towards Evidence-Faithful Video Anomaly Understanding via Agentic Search
73. NeurIPS 2026Semantic Search over 9 Million Mathematical Theorems
74. NeurIPS 2026SGEvolve: Semantic Gradient Guidance for LLM-Driven Evolutionary Search
75. NeurIPS 2026SMART: Scalable Multi-Agent Role-conditioned Teaming via LLM-free Tree Search
76. NeurIPS 2026Smoothed Score Queries and the Complexity of Sampling
77. NeurIPS 2026SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
78. NeurIPS 2026SpecForge: Agent-Oriented Code Documentation Optimization via Multi-Frontier Tree Search
79. NeurIPS 2026Stabilizing RL+Search for Imperfect-Information Extensive-Form Games
80. NeurIPS 2026StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search
81. NeurIPS 2026Stochastic Optimization with Random Search
82. NeurIPS 2026Test Time Search Requires Training for Diversity
83. NeurIPS 2026The Query Complexity of Local Search in Rounds on General Graphs
84. NeurIPS 2026Transformers Provably Learn Graph Search: Training Dynamics and the Exponential Power of Depth
85. NeurIPS 2026Tree Rotary Positional Encoding for Extreme Length Extrapolation from Scratch
86. NeurIPS 2026Tree Search With Predictions
87. NeurIPS 2026Tree Training: Efficient LLM Training on Tree-Structured Trajectories
88. NeurIPS 2026Tree-Ensemble Repair through Constrained Optimization
89. NeurIPS 2026Tree-Guided Identify Then Exploit: A Unified Framework of Pure Exploration and Regret Minimization for Dueling Bandits
90. NeurIPS 2026Tree-Sliced Orlicz Integral Probability Metric
91. NeurIPS 2026Tree-Structured Synergy of Large Language Models and Bayesian Optimization for Efficient CASH
92. NeurIPS 2026TreeWalker: Partial Evaluation for Grouped Tree-Ensemble Inference
93. NeurIPS 2026Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning
94. NeurIPS 2026TUBE: Tangent Upper Bound on Evidence for Discrete Diffusion Language Models
95. NeurIPS 2026Two-Fidelity Best-Action Identification for Stochastic Minimax Tree
96. NeurIPS 2026Understanding Randomization in Greedy Model Search
97. NeurIPS 2026Variance Reduction for Expectations with Diffusion Teachers
98. NeurIPS 2026Variational Inference via Entropic Transport Descent
99. NeurIPS 2026VisInteract: Towards Dynamic Interactive Text-to-Visualization under Imperfect Queries

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。