Exploration-Exploitation papers, 2023–2026

Key findings

• Exploration-Exploitation went from 47 papers in 2023 to 71 in 2026, roughly 1.5x in three years.
• NeurIPS publishes the most Exploration-Exploitation work: 93 papers from 2023 to 2026, 40% of the four-venue total.
• The fastest-growing overlap is with Reasoning Models: papers tagged with both rose from 1 in 2023 to 10 in 2026.
• Among the 5 topics under Recommenders and Ads, it ranks #4 by 2026 paper count; the fastest grower in the group, Click-Through Prediction, is up 2.6x versus 1.5x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Exploration-Exploitation papers

235 papers, page 2 of 5

51. NeurIPS 2026Decentralized Q-Learning in Markov Potential Games
52. NeurIPS 2026ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection
53. NeurIPS 2026Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL
54. NeurIPS 2026Hit Expansion via Localized Exploration of Synthesizable Chemical Space
55. NeurIPS 2026LACE: Lattice Attention for Cross-thread Exploration
56. NeurIPS 2026Near-Optimal Best-of-Both-Worlds Algorithms for Decoupled Exploration and Exploitation in Multi-armed Bandits
57. NeurIPS 2026Not all uncertainty is alike: volatility, stochasticity, and exploration
58. NeurIPS 2026Online Decision-Focused Learning under Semi-Bandit Feedback
59. NeurIPS 2026Optimal Recalibration of an Online Predictor
60. NeurIPS 2026PAC Learning with Bandit Feedback: Sharp Sample Complexity in the Realizable Setting
61. NeurIPS 2026Parameter Exploration for RLVR via Variational Learning
62. NeurIPS 2026Pure Exploration Beyond Reward Feedback: The Role of Post-Action Context
63. NeurIPS 2026Regret–Oracle Complexity Tradeoffs in Agnostic Online Learning
64. NeurIPS 2026ScreenSearch: Uncertainty-Aware OS Exploration
65. NeurIPS 2026Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and Exploitation
66. NeurIPS 2026Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck
67. NeurIPS 2026TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs
68. NeurIPS 2026The Illusion of Diversity: Aligning LLM Exploration via Effective Entropy
69. NeurIPS 2026The Power of a Random Sample in Online Algorithms
70. NeurIPS 2026Tree-Guided Identify Then Exploit: A Unified Framework of Pure Exploration and Regret Minimization for Dueling Bandits
71. NeurIPS 2026Value-Priced Uncertainty: A Family of PPO-Compatible Exploration Bonuses
72. CVPR 2025Dynamic Pseudo Labeling via Gradient Cutting for High-Low Entropy Exploration
73. CVPR 2025GUI-Xplore: Empowering Generalizable GUI Agents with One Exploration
74. CVPR 2025Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation
75. ICLR 2025B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
76. ICLR 2025Bandit Learning in Matching Markets with Indifference
77. ICLR 2025Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration
78. ICLR 2025Brain Bandit: A Biologically Grounded Neural Network for Efficient Control of Exploration
79. ICLR 2025Breaking the $\log(1/\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids
80. ICLR 2025Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts
81. ICLR 2025From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
82. ICLR 2025Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning
83. ICLR 2025kNN Attention Demystified: A Theoretical Exploration for Scalable Transformers
84. ICLR 2025Online Preference Alignment for Language Models via Count-based Exploration
85. ICML 2025Catching Two Birds with One Stone: Reward Shaping with Dual Random Networks for Balancing Exploration and Exploitation
86. ICML 2025Clustering Items through Bandit Feedback: Finding the Right Feature out of Many
87. ICML 2025Constrained Pareto Set Identification with Bandit Feedback
88. ICML 2025Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story
89. ICML 2025EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration
90. ICML 2025Fixed-Confidence Multiple Change Point Identification under Bandit Feedback
91. ICML 2025Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification
92. ICML 2025Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning
93. ICML 2025Instance-Optimal Pure Exploration for Linear Bandits on Continuous Arms
94. ICML 2025KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies
95. ICML 2025Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit Feedback
96. ICML 2025Learning Safe Control via On-the-Fly Bandit Exploration
97. ICML 2025Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
98. ICML 2025Model-Based Exploration in Monitored Markov Decision Processes
99. ICML 2025Near Optimal Best Arm Identification for Clustered Bandits
100. ICML 2025Near Optimal Non-asymptotic Sample Complexity of 1-Identification

FAQ

How many Exploration-Exploitation papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

235 in total: 47 in 2023, 63 in 2024, 54 in 2025, 71 in 2026.

How many Exploration-Exploitation papers are at NeurIPS 2026?

NeurIPS 2026 has 25 Exploration-Exploitation papers, versus 20 the year before.

How many Exploration-Exploitation papers are at ICLR 2026?

ICLR 2026 has 23 Exploration-Exploitation papers, versus 10 the year before.

How many Exploration-Exploitation papers are at ICML 2026?

ICML 2026 has 19 Exploration-Exploitation papers, versus 21 the year before.

How many Exploration-Exploitation papers are at CVPR 2026?

CVPR 2026 has 4 Exploration-Exploitation papers, versus 3 the year before.

Which conference publishes the most Exploration-Exploitation papers?

NeurIPS, with 93 papers from 2023 to 2026.