多智能体 RL论文趋势 2023–2026

博弈与 MARL

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 2,126 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

多智能体 RL论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023883780106311
20241473982105373
202525591115113574
2026319153224172868

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

全部多智能体 RL论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 2,126 篇，第 28 / 43 页

  1. NeurIPS 2025Multi-Token Prediction Needs Registers
  2. NeurIPS 2025Multi-View Oriented GPLVM: Expressiveness and Efficiency
  3. NeurIPS 2025Multimodal Bandits: Regret Lower Bounds and Optimal Algorithms
  4. NeurIPS 2025MultiNet: Adaptive Multi-Viewed Subgraph Convolutional Networks for Graph Classification
  5. NeurIPS 2025MURKA: Multi-Reward Reinforcement Learning with Knowledge Alignment for Optimization Tasks
  6. NeurIPS 2025MVSMamba: Multi-View Stereo with State Space Model
  7. NeurIPS 2025Noisy Multi-Label Learning through Co-Occurrence-Aware Diffusion
  8. NeurIPS 2025OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation
  9. NeurIPS 2025On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning
  10. NeurIPS 2025On the Convergence of Stochastic Smoothed Multi-Level Compositional Gradient Descent Ascent
  11. NeurIPS 2025On the sample complexity of semi-supervised multi-objective learning
  12. NeurIPS 2025Online Multi-Class Selection with Group Fairness Guarantee
  13. NeurIPS 2025OPHR: Mastering Volatility Trading with Multi-Agent Deep Reinforcement Learning
  14. NeurIPS 2025Opinion Maximization in Social Networks by Modifying Internal Opinions
  15. NeurIPS 2025Optimal Estimation of the Best Mean in Multi-Armed Bandits
  16. NeurIPS 2025Optimal Spectral Transitions in High-Dimensional Multi-Index Models
  17. NeurIPS 2025Optimism Without Regularization: Constant Regret in Zero-Sum Games
  18. NeurIPS 2025OrbitZoo: Real Orbital Systems Challenges for Reinforcement Learning
  19. NeurIPS 2025Oryx: a Scalable Sequence Model for Many-Agent Coordination in Offline MARL
  20. NeurIPS 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
  21. NeurIPS 2025OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis
  22. NeurIPS 2025PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization
  23. NeurIPS 2025Pareto Optimal Risk-Agnostic Distributional Bandits with Heavy-Tail Rewards
  24. NeurIPS 2025Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)
  25. NeurIPS 2025PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation
  26. NeurIPS 2025Planning with Quantized Opponent Models
  27. NeurIPS 2025PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement
  28. NeurIPS 2025Policy Gradient Methods Converge Globally in Imperfect-Information Extensive-Form Games
  29. NeurIPS 2025Probably Approximately Precision and Recall Learning
  30. NeurIPS 2025Protocols for Verifying Smooth Strategies in Bandits and Games
  31. NeurIPS 2025Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths
  32. NeurIPS 2025Put CASH on Bandits: A Max K-Armed Problem for Automated Machine Learning
  33. NeurIPS 2025R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization
  34. NeurIPS 2025Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Observation Delays
  35. NeurIPS 2025Rationalized All-Atom Protein Design with Unified Multi-Modal Bayesian Flow
  36. NeurIPS 2025Regret Lower Bounds for Decentralized Multi-Agent Stochastic Shortest Path Problems
  37. NeurIPS 2025Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning
  38. NeurIPS 2025ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model
  39. NeurIPS 2025Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies
  40. NeurIPS 2025ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning
  41. NeurIPS 2025Retro-R1: LLM-based Agentic Retrosynthesis
  42. NeurIPS 2025Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
  43. NeurIPS 2025Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
  44. NeurIPS 2025Role-aware Multi-agent Reinforcement Learning for Coordinated Emergency Traffic Control
  45. NeurIPS 2025Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning
  46. NeurIPS 2025SAINT: Sequence-Aware Integration for Spatial Transcriptomics Multi-View Clustering
  47. NeurIPS 2025SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models
  48. NeurIPS 2025Sample-Adaptivity Tradeoff in On-Demand Sampling
  49. NeurIPS 2025Sample-Efficient Tabular Self-Play for Offline Robust Reinforcement Learning
  50. NeurIPS 2025Sampling from multi-modal distributions with polynomial query complexity in fixed dimension via reverse diffusion

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 查多智能体 RL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": "multi-agent-rl"}

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多智能体 RL论文？
共 2,126 篇，按年份分别是 2023 年 311 篇、2024 年 373 篇、2025 年 574 篇、2026 年 868 篇。
NeurIPS 2026 有多少篇多智能体 RL论文？
NeurIPS 2026 有 319 篇多智能体 RL论文，上一届是 255 篇。
ICLR 2026 有多少篇多智能体 RL论文？
ICLR 2026 有 153 篇多智能体 RL论文，上一届是 91 篇。
ICML 2026 有多少篇多智能体 RL论文？
ICML 2026 有 224 篇多智能体 RL论文，上一届是 115 篇。
CVPR 2026 有多少篇多智能体 RL论文？
CVPR 2026 有 172 篇多智能体 RL论文，上一届是 113 篇。
哪个会议的多智能体 RL论文最多？
NeurIPS，2023–2026 年共 809 篇。

「博弈与规划」下的其他主题