探索利用论文趋势 2023–2026

主要结论

• 探索利用论文从 2023 年的 47 篇增长到 2026 年的 71 篇，三年间扩大到约 1.5 倍。
• NeurIPS 是发探索利用论文最多的会议，2023–2026 年共 93 篇，占四个会议总量的 40%。
• 交叉方向里涨得最快的是推理模型：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 10 篇。
• 在「推荐与广告」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的点击率预测是 2.6 倍，探索利用是 1.5 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 2026Decentralized Q-Learning in Markov Potential Games
• ICML 2026Bandit Social Leaning Dynamics with Exploration Episodes
• ICLR 2026Laplacian Kernelized Bandit
• CVPR 2026Underground Plant Exploration Non-Destructive 3D Root Assessment with GPR Based
• NeurIPS 2025DUET: Dual-Perspective Pseudo Labeling and Uncertainty-aware Exploration & Exploitation Training for Source-Free Domain Adaptation
• ICML 2025Clustering Items through Bandit Feedback: Finding the Right Feature out of Many
• ICLR 2025B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
• CVPR 2025Dynamic Pseudo Labeling via Gradient Cutting for High-Low Entropy Exploration
• NeurIPS 2024Exploration, Exploitation, and Engagement in Multi-Armed Bandits with Abandonment
• ICML 2024A Contextual Combinatorial Bandit Approach to Negotiation
• ICLR 2024Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation
• CVPR 2024Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation
• NeurIPS 2023Adaptive Algorithms for Relaxed Pareto Set Identification
• ICML 2023Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments
• ICLR 2023Combinatorial Pure Exploration of Causal Bandits
• CVPR 2023Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields
• NeurIPS 2026Hit Expansion via Localized Exploration of Synthesizable Chemical Space
• ICML 2026Exploration-free Algorithms for Multi-group Mean Estimation
• ICLR 2026DIVERSE: Disagreement-Inducing Vector Evolution for Rashomon Set Exploration
• CVPR 2026From Exploration to Exploitation A Two-Stage Entropy RLVR Approach for

全部探索利用论文

共 235 篇，第 3 / 5 页

101. ICML 2025Optimal and Practical Batched Linear Bandit Algorithm
102. ICML 2025Provably Efficient Exploration in Inverse Constrained Reinforcement Learning
103. ICML 2025The Batch Complexity of Bandit Pure Exploration
104. ICML 2025The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback
105. ICML 2025Zero-Inflated Bandits
106. NeurIPS 2025Balancing Performance and Costs in Best Arm Identification
107. NeurIPS 2025Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration
108. NeurIPS 2025Deployment Efficient Reward-Free Exploration with Linear Function Approximation
109. NeurIPS 2025DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning
110. NeurIPS 2025DUET: Dual-Perspective Pseudo Labeling and Uncertainty-aware Exploration & Exploitation Training for Source-Free Domain Adaptation
111. NeurIPS 2025Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL
112. NeurIPS 2025Exploration via Feature Perturbation in Contextual Bandits
113. NeurIPS 2025From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards
114. NeurIPS 2025Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts
115. NeurIPS 2025Imagine Beyond ! Distributionally Robust Autoencoding for State Space Coverage in Online Reinforcement Learning
116. NeurIPS 2025Infrequent Exploration in Linear Bandits
117. NeurIPS 2025Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring
118. NeurIPS 2025Non-Uniform Multiclass Learning with Bandit Feedback
119. NeurIPS 2025Novel Exploration via Orthogonality
120. NeurIPS 2025Order-Level Attention Similarity Across Language Models: A Latent Commonality
121. NeurIPS 2025Reinforcement Learning with Action Chunking
122. NeurIPS 2025Scalable Exploration via Ensemble++
123. NeurIPS 2025True Impact of Cascade Length in Contextual Cascading Bandits
124. NeurIPS 2025Uncertainty-Guided Exploration for Efficient AlphaZero Training
125. NeurIPS 2025Unveiling Transformer Perception by Exploring Input Manifolds
126. CVPR 2024Accept the Modality Gap: An Exploration in the Hyperbolic Space
127. CVPR 2024Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation
128. ICLR 2024Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation
129. ICLR 2024Improving Intrinsic Exploration by Creating Stationary Objectives
130. ICLR 2024In-context Exploration-Exploitation for Reinforcement Learning
131. ICLR 2024Neural Active Learning Beyond Bandits
132. ICLR 2024The Curse of Diversity in Ensemble-Based Exploration
133. ICLR 2024Unlocking the Power of Representations in Long-term Novelty-based Exploration
134. ICML 2024A Contextual Combinatorial Bandit Approach to Negotiation
135. ICML 2024Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
136. ICML 2024BAGEL: Bootstrapping Agents by Guiding Exploration with Language
137. ICML 2024Bayesian Exploration Networks
138. ICML 2024Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin Dynamics
139. ICML 2024Efficient Exploration for LLMs
140. ICML 2024Exploration and Anti-Exploration with Distributional Random Network Distillation
141. ICML 2024Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
142. ICML 2024Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach
143. ICML 2024Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction
144. ICML 2024Handling Heterogeneous Curvatures in Bandit LQR Control
145. ICML 2024Imitation Learning in Discounted Linear MDPs without exploration assumptions
146. ICML 2024Online Learning with Bounded Recall
147. ICML 2024Online Resource Allocation with Non-Stationary Customers
148. ICML 2024Optimal Batched Linear Bandits
149. ICML 2024Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret
150. ICML 2024Provably Efficient Long-Horizon Exploration in Monte Carlo Tree Search through State Occupancy Regularization

常见问题

2023–2026 年四大会议一共有多少篇探索利用论文？

共 235 篇，按年份分别是 2023 年 47 篇、2024 年 63 篇、2025 年 54 篇、2026 年 71 篇。

NeurIPS 2026 有多少篇探索利用论文？

NeurIPS 2026 有 25 篇探索利用论文，上一届是 20 篇。

ICLR 2026 有多少篇探索利用论文？

ICLR 2026 有 23 篇探索利用论文，上一届是 10 篇。

ICML 2026 有多少篇探索利用论文？

ICML 2026 有 19 篇探索利用论文，上一届是 21 篇。

CVPR 2026 有多少篇探索利用论文？

CVPR 2026 有 4 篇探索利用论文，上一届是 3 篇。

哪个会议的探索利用论文最多？

NeurIPS，2023–2026 年共 93 篇。