强化学习论文趋势 2023–2026

策略优化、离线 RL 与基于环境的决策学习

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 6,885 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

强化学习论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023484233297561,070
2024466304356641,190
2025784379405721,640
20267609111,0212932,985

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

全部强化学习论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 784 篇，第 6 / 16 页

  1. NeurIPS 2025GPO: Learning from Critical Steps to Improve LLM Reasoning
  2. NeurIPS 2025Graph Neural Network Based Action Ranking for Planning
  3. NeurIPS 2025GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining
  4. NeurIPS 2025Greedy Sampling Is Provably Efficient For RLHF
  5. NeurIPS 2025GRIT: Teaching MLLMs to Think with Images
  6. NeurIPS 2025Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data
  7. NeurIPS 2025Grounded Reinforcement Learning for Visual Reasoning
  8. NeurIPS 2025Group-in-Group Policy Optimization for LLM Agent Training
  9. NeurIPS 2025GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
  10. NeurIPS 2025GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning
  11. NeurIPS 2025GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents
  12. NeurIPS 2025GUI-Rise: Structured Reasoning and History Summarization for GUI Navigation
  13. NeurIPS 2025Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment
  14. NeurIPS 2025GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
  15. NeurIPS 2025Gymnasium: A Standard Interface for Reinforcement Learning Environments
  16. NeurIPS 2025Hadamax Encoding: Elevating Performance in Model-Free Atari
  17. NeurIPS 2025HCRMP: An LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving
  18. NeurIPS 2025HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages
  19. NeurIPS 2025Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradation
  20. NeurIPS 2025Heterogeneous Graph Transformers for Simultaneous Mobile Multi-Robot Task Allocation and Scheduling under Temporal Constraints
  21. NeurIPS 2025Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems
  22. NeurIPS 2025Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation
  23. NeurIPS 2025High-Dimensional Calibration from Swap Regret
  24. NeurIPS 2025High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning
  25. NeurIPS 2025HMARL-CBF – Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems
  26. NeurIPS 2025Horizon Reduction Makes RL Scalable
  27. NeurIPS 2025How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learning
  28. NeurIPS 2025How Far Are We from Optimal Reasoning Efficiency?
  29. NeurIPS 2025How to Train Your LLM Web Agent: A Statistical Diagnosis
  30. NeurIPS 2025Human-assisted Robotic Policy Refinement via Action Preference Optimization
  31. NeurIPS 2025Hybrid Latent Reasoning via Reinforcement Learning
  32. NeurIPS 2025HyperMARL: Adaptive Hypernetworks for Multi-Agent RL
  33. NeurIPS 2025Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMs
  34. NeurIPS 2025HYPRL: Reinforcement Learning of Control Policies for Hyperproperties
  35. NeurIPS 2025Imagine Beyond ! Distributionally Robust Autoencoding for State Space Coverage in Online Reinforcement Learning
  36. NeurIPS 2025Imagined Autocurricula
  37. NeurIPS 2025Imitation Beyond Expectation Using Pluralistic Stochastic Dominance
  38. NeurIPS 2025Imitation Learning with Temporal Logic Constraints
  39. NeurIPS 2025Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections
  40. NeurIPS 2025Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
  41. NeurIPS 2025Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
  42. NeurIPS 2025Improving Model-Based Reinforcement Learning by Converging to Flatter Minima
  43. NeurIPS 2025Improving Monte Carlo Tree Search for Symbolic Regression
  44. NeurIPS 2025Improving planning and MBRL with temporally-extended actions
  45. NeurIPS 2025Improving Regret Approximation for Unsupervised Dynamic Environment Generation
  46. NeurIPS 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
  47. NeurIPS 2025Improving Reward Models with Proximal Policy Exploration for Preference-Based Reinforcement Learning
  48. NeurIPS 2025Improving Video Generation with Human Feedback
  49. NeurIPS 2025In-Context Fully Decentralized Cooperative Multi-Agent Reinforcement Learning
  50. NeurIPS 2025Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning

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 查强化学习在 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": "reinforcement-learning"}

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强化学习论文？
共 6,885 篇，按年份分别是 2023 年 1,070 篇、2024 年 1,190 篇、2025 年 1,640 篇、2026 年 2,985 篇。
NeurIPS 2026 有多少篇强化学习论文？
NeurIPS 2026 有 760 篇强化学习论文，上一届是 784 篇。
ICLR 2026 有多少篇强化学习论文？
ICLR 2026 有 911 篇强化学习论文，上一届是 379 篇。
ICML 2026 有多少篇强化学习论文？
ICML 2026 有 1,021 篇强化学习论文，上一届是 405 篇。
CVPR 2026 有多少篇强化学习论文？
CVPR 2026 有 293 篇强化学习论文，上一届是 72 篇。
哪个会议的强化学习论文最多？
NeurIPS，2023–2026 年共 2,494 篇。