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 93 篇，第 1 / 2 页

  1. NeurIPS 2026Agnostic Online Learning with Reliable Abstention
  2. NeurIPS 2026Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models
  3. NeurIPS 2026CIG: Exploration via Conditional Information Gain
  4. NeurIPS 2026Contrastive Pretraining Scales Agentic Exploration
  5. NeurIPS 2026Decentralized Q-Learning in Markov Potential Games
  6. NeurIPS 2026ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection
  7. NeurIPS 2026Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL
  8. NeurIPS 2026Hit Expansion via Localized Exploration of Synthesizable Chemical Space
  9. NeurIPS 2026LACE: Lattice Attention for Cross-thread Exploration
  10. NeurIPS 2026Near-Optimal Best-of-Both-Worlds Algorithms for Decoupled Exploration and Exploitation in Multi-armed Bandits
  11. NeurIPS 2026Not all uncertainty is alike: volatility, stochasticity, and exploration
  12. NeurIPS 2026Online Decision-Focused Learning under Semi-Bandit Feedback
  13. NeurIPS 2026Optimal Recalibration of an Online Predictor
  14. NeurIPS 2026PAC Learning with Bandit Feedback: Sharp Sample Complexity in the Realizable Setting
  15. NeurIPS 2026Parameter Exploration for RLVR via Variational Learning
  16. NeurIPS 2026Pure Exploration Beyond Reward Feedback: The Role of Post-Action Context
  17. NeurIPS 2026Regret–Oracle Complexity Tradeoffs in Agnostic Online Learning
  18. NeurIPS 2026ScreenSearch: Uncertainty-Aware OS Exploration
  19. NeurIPS 2026Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and Exploitation
  20. NeurIPS 2026Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck
  21. NeurIPS 2026TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs
  22. NeurIPS 2026The Illusion of Diversity: Aligning LLM Exploration via Effective Entropy
  23. NeurIPS 2026The Power of a Random Sample in Online Algorithms
  24. NeurIPS 2026Tree-Guided Identify Then Exploit: A Unified Framework of Pure Exploration and Regret Minimization for Dueling Bandits
  25. NeurIPS 2026Value-Priced Uncertainty: A Family of PPO-Compatible Exploration Bonuses
  26. NeurIPS 2025Balancing Performance and Costs in Best Arm Identification
  27. NeurIPS 2025Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration
  28. NeurIPS 2025Deployment Efficient Reward-Free Exploration with Linear Function Approximation
  29. NeurIPS 2025DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning
  30. NeurIPS 2025DUET: Dual-Perspective Pseudo Labeling and Uncertainty-aware Exploration & Exploitation Training for Source-Free Domain Adaptation
  31. NeurIPS 2025Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL
  32. NeurIPS 2025Exploration via Feature Perturbation in Contextual Bandits
  33. NeurIPS 2025From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards
  34. NeurIPS 2025Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts
  35. NeurIPS 2025Imagine Beyond ! Distributionally Robust Autoencoding for State Space Coverage in Online Reinforcement Learning
  36. NeurIPS 2025Infrequent Exploration in Linear Bandits
  37. NeurIPS 2025Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring
  38. NeurIPS 2025Non-Uniform Multiclass Learning with Bandit Feedback
  39. NeurIPS 2025Novel Exploration via Orthogonality
  40. NeurIPS 2025Order-Level Attention Similarity Across Language Models: A Latent Commonality
  41. NeurIPS 2025Reinforcement Learning with Action Chunking
  42. NeurIPS 2025Scalable Exploration via Ensemble++
  43. NeurIPS 2025True Impact of Cascade Length in Contextual Cascading Bandits
  44. NeurIPS 2025Uncertainty-Guided Exploration for Efficient AlphaZero Training
  45. NeurIPS 2025Unveiling Transformer Perception by Exploring Input Manifolds
  46. NeurIPS 2024Bandits with Preference Feedback: A Stackelberg Game Perspective
  47. NeurIPS 2024Beyond Optimism: Exploration With Partially Observable Rewards
  48. NeurIPS 2024Code Repair with LLMs gives an Exploration-Exploitation Tradeoff
  49. NeurIPS 2024Effective Exploration Based on the Structural Information Principles
  50. NeurIPS 2024Exploration by Learning Diverse Skills through Successor State Representations

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