Monte Carlo Tree Search papers, 2023–2026

Key findings

• Monte Carlo Tree Search went from 115 papers in 2023 to 278 in 2026, roughly 2.4x in three years.
• NeurIPS publishes the most Monte Carlo Tree Search work: 302 papers from 2023 to 2026, 39% of the four-venue total.
• The fastest-growing overlap is with AI Agents: papers tagged with both rose from 1 in 2023 to 26 in 2026.
• Among the 5 topics under Games and Planning, it ranks #3 by 2026 paper count; the fastest grower in the group, Classical Planning, is up 3.3x versus 2.4x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Monte Carlo Tree Search papers

170 papers, page 2 of 4

51. ICLR 2026ToolTree: Efficient LLM Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning
52. ICLR 2026Towards Better Branching Policies: Leveraging the Sequential Nature of Branch-and-Bound Tree
53. ICLR 2026Tree Search for LLM Agent Reinforcement Learning
54. ICLR 2026Tree-sliced Sobolev IPM
55. ICLR 2026TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models
56. ICLR 2026Unlocking Long-Horizon Agentic Search with Large-Scale End-to-End RL
57. ICLR 2026VFScale: Intrinsic Reasoning through Verifier-Free Test-time Scalable Diffusion Model
58. ICLR 2026Weak-to-Strong Generalization with Failure Trajectories
59. ICLR 2026Welfarist Formulations for Diverse Similarity Search
60. ICLR 2026What Generative Search Engines Like and How to Optimize Web Content Cooperatively
61. ICLR 2025Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods
62. ICLR 2025BTBS-LNS: Binarized-Tightening, Branch and Search on Learning LNS Policies for MIP
63. ICLR 2025CARTS: Advancing Neural Theorem Proving with Diversified Tactic Calibration and Bias-Resistant Tree Search
64. ICLR 2025Decision Tree Induction Through LLMs via Semantically-Aware Evolution
65. ICLR 2025DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search
66. ICLR 2025DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference
67. ICLR 2025Distance-Based Tree-Sliced Wasserstein Distance
68. ICLR 2025DPaI: Differentiable Pruning at Initialization with Node-Path Balance Principle
69. ICLR 2025Epistemic Monte Carlo Tree Search
70. ICLR 2025ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning
71. ICLR 2025Fast Summation of Radial Kernels via QMC Slicing
72. ICLR 2025Fast unsupervised ground metric learning with tree-Wasserstein distance
73. ICLR 2025From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs
74. ICLR 2025Human-Aligned Chess With a Bit of Search
75. ICLR 2025Implicit Search via Discrete Diffusion: A Study on Chess
76. ICLR 2025In Search of Forgotten Domain Generalization
77. ICLR 2025KinFormer: Generalizable Dynamical Symbolic Regression for Catalytic Organic Reaction Kinetics
78. ICLR 2025Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning
79. ICLR 2025Learning Evolving Tools for Large Language Models
80. ICLR 2025Learning to Select Nodes in Branch and Bound with Sufficient Tree Representation
81. ICLR 2025Learning-Augmented Search Data Structures
82. ICLR 2025Linear Mode Connectivity in Differentiable Tree Ensembles
83. ICLR 2025Linear Transformer Topological Masking with Graph Random Features
84. ICLR 2025Monte Carlo Planning with Large Language Model for Text-Based Game Agents
85. ICLR 2025Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detection
86. ICLR 2025Pacmann: Efficient Private Approximate Nearest Neighbor Search
87. ICLR 2025Parameter Expanded Stochastic Gradient Markov Chain Monte Carlo
88. ICLR 2025Procedural Synthesis of Synthesizable Molecules
89. ICLR 2025Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling
90. ICLR 2025Qinco2: Vector Compression and Search with Improved Implicit Neural Codebooks
91. ICLR 2025Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?
92. ICLR 2025RuAG: Learned-rule-augmented Generation for Large Language Models
93. ICLR 2025Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction
94. ICLR 2025Sequential Controlled Langevin Diffusions
95. ICLR 2025SFS: Smarter Code Space Search improves LLM Inference Scaling
96. ICLR 2025SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
97. ICLR 2025Spherical Tree-Sliced Wasserstein Distance
98. ICLR 2025Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo
99. ICLR 2025Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search
100. ICLR 2025Strength Estimation and Human-Like Strength Adjustment in Games

FAQ

How many Monte Carlo Tree Search papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

773 in total: 115 in 2023, 144 in 2024, 236 in 2025, 278 in 2026.

How many Monte Carlo Tree Search papers are at NeurIPS 2026?

NeurIPS 2026 has 99 Monte Carlo Tree Search papers, versus 100 the year before.

How many Monte Carlo Tree Search papers are at ICLR 2026?

ICLR 2026 has 60 Monte Carlo Tree Search papers, versus 49 the year before.

How many Monte Carlo Tree Search papers are at ICML 2026?

ICML 2026 has 105 Monte Carlo Tree Search papers, versus 75 the year before.

How many Monte Carlo Tree Search papers are at CVPR 2026?

CVPR 2026 has 14 Monte Carlo Tree Search papers, versus 12 the year before.

Which conference publishes the most Monte Carlo Tree Search papers?

NeurIPS, with 302 papers from 2023 to 2026.