探索利用论文趋势 2023–2026

Bandit 在线学习

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 235 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

探索利用论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202318919147
202430625263
2025201021354
2026252319471

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

全部探索利用论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 54 篇，第 1 / 2 页

  1. CVPR 2025Dynamic Pseudo Labeling via Gradient Cutting for High-Low Entropy Exploration
  2. CVPR 2025GUI-Xplore: Empowering Generalizable GUI Agents with One Exploration
  3. CVPR 2025Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation
  4. ICLR 2025B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
  5. ICLR 2025Bandit Learning in Matching Markets with Indifference
  6. ICLR 2025Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration
  7. ICLR 2025Brain Bandit: A Biologically Grounded Neural Network for Efficient Control of Exploration
  8. ICLR 2025Breaking the $\log(1/\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids
  9. ICLR 2025Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts
  10. ICLR 2025From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
  11. ICLR 2025Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning
  12. ICLR 2025kNN Attention Demystified: A Theoretical Exploration for Scalable Transformers
  13. ICLR 2025Online Preference Alignment for Language Models via Count-based Exploration
  14. ICML 2025Catching Two Birds with One Stone: Reward Shaping with Dual Random Networks for Balancing Exploration and Exploitation
  15. ICML 2025Clustering Items through Bandit Feedback: Finding the Right Feature out of Many
  16. ICML 2025Constrained Pareto Set Identification with Bandit Feedback
  17. ICML 2025Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story
  18. ICML 2025EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration
  19. ICML 2025Fixed-Confidence Multiple Change Point Identification under Bandit Feedback
  20. ICML 2025Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification
  21. ICML 2025Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning
  22. ICML 2025Instance-Optimal Pure Exploration for Linear Bandits on Continuous Arms
  23. ICML 2025KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies
  24. ICML 2025Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit Feedback
  25. ICML 2025Learning Safe Control via On-the-Fly Bandit Exploration
  26. ICML 2025Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
  27. ICML 2025Model-Based Exploration in Monitored Markov Decision Processes
  28. ICML 2025Near Optimal Best Arm Identification for Clustered Bandits
  29. ICML 2025Near Optimal Non-asymptotic Sample Complexity of 1-Identification
  30. ICML 2025Optimal and Practical Batched Linear Bandit Algorithm
  31. ICML 2025Provably Efficient Exploration in Inverse Constrained Reinforcement Learning
  32. ICML 2025The Batch Complexity of Bandit Pure Exploration
  33. ICML 2025The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback
  34. ICML 2025Zero-Inflated Bandits
  35. NeurIPS 2025Balancing Performance and Costs in Best Arm Identification
  36. NeurIPS 2025Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration
  37. NeurIPS 2025Deployment Efficient Reward-Free Exploration with Linear Function Approximation
  38. NeurIPS 2025DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning
  39. NeurIPS 2025DUET: Dual-Perspective Pseudo Labeling and Uncertainty-aware Exploration & Exploitation Training for Source-Free Domain Adaptation
  40. NeurIPS 2025Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL
  41. NeurIPS 2025Exploration via Feature Perturbation in Contextual Bandits
  42. NeurIPS 2025From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards
  43. NeurIPS 2025Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts
  44. NeurIPS 2025Imagine Beyond ! Distributionally Robust Autoencoding for State Space Coverage in Online Reinforcement Learning
  45. NeurIPS 2025Infrequent Exploration in Linear Bandits
  46. NeurIPS 2025Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring
  47. NeurIPS 2025Non-Uniform Multiclass Learning with Bandit Feedback
  48. NeurIPS 2025Novel Exploration via Orthogonality
  49. NeurIPS 2025Order-Level Attention Similarity Across Language Models: A Latent Commonality
  50. NeurIPS 2025Reinforcement Learning with Action Chunking

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查探索利用在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "exploration-exploitation"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「推荐与广告」下的其他主题