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 574 篇，第 6 / 12 页

  1. ICML 2025G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks
  2. ICML 2025GradPS: Resolving Futile Neurons in Parameter Sharing Network for Multi-Agent Reinforcement Learning
  3. ICML 2025GTR: A General, Multi-View, and Dynamic Framework for Trajectory Representation Learning
  4. ICML 2025How to Train Your Multi-Exit Model? Analyzing the Impact of Training Strategies
  5. ICML 2025Hybrid Quantum-Classical Multi-Agent Pathfinding
  6. ICML 2025HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning
  7. ICML 2025Improving Multi-Class Calibration through Normalization-Aware Isotonic Techniques
  8. ICML 2025Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games
  9. ICML 2025KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems
  10. ICML 2025Learning from True-False Labels via Multi-modal Prompt Retrieving
  11. ICML 2025Learning Mean Field Control on Sparse Graphs
  12. ICML 2025Learning Progress Driven Multi-Agent Curriculum
  13. ICML 2025Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization
  14. ICML 2025Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals
  15. ICML 2025Learning to Steer Learners in Games
  16. ICML 2025Learning to Stop: Deep Learning for Mean Field Optimal Stopping
  17. ICML 2025Linear Contextual Bandits With Interference
  18. ICML 2025LLM-Assisted Semantically Diverse Teammate Generation for Efficient Multi-agent Coordination
  19. ICML 2025M³HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality
  20. ICML 2025MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
  21. ICML 2025MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines
  22. ICML 2025MoH: Multi-Head Attention as Mixture-of-Head Attention
  23. ICML 2025MoRAgent: Parameter Efficient Agent Tuning with Mixture-of-Roles
  24. ICML 2025Multi-agent Architecture Search via Agentic Supernet
  25. ICML 2025Multi-Armed Bandits with Interference: Bridging Causal Inference and Adversarial Bandits
  26. ICML 2025Multi-band Frequency Reconstruction for Neural Psychoacoustic Coding
  27. ICML 2025Multi-objective Linear Reinforcement Learning with Lexicographic Rewards
  28. ICML 2025Multi-View Graph Clustering via Node-Guided Contrastive Encoding
  29. ICML 2025MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary Decomposition
  30. ICML 2025Near Optimal Best Arm Identification for Clustered Bandits
  31. ICML 2025Nemotron-CORTEXA: Enhancing LLM Agents for Software Engineering Tasks via Improved Localization and Solution Diversity
  32. ICML 2025O-MAPL: Offline Multi-agent Preference Learning
  33. ICML 2025Observation Interference in Partially Observable Assistance Games
  34. ICML 2025Offline Learning for Combinatorial Multi-armed Bandits
  35. ICML 2025On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents
  36. ICML 2025OrcaLoca: An LLM Agent Framework for Software Issue Localization
  37. ICML 2025Pairwise Maximum Likelihood For Multi-Class Logistic Regression Model With Multiple Rare Classes
  38. ICML 2025PokéChamp: an Expert-level Minimax Language Agent
  39. ICML 2025Position: Build Agent Advocates, Not Platform Agents
  40. ICML 2025Position: Theory of Mind Benchmarks are Broken for Large Language Models
  41. ICML 2025Position: Uncertainty Quantification Needs Reassessment for Large Language Model Agents
  42. ICML 2025Prediction-Aware Learning in Multi-Agent Systems
  43. ICML 2025Preference Controllable Reinforcement Learning with Advanced Multi-Objective Optimization
  44. ICML 2025Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents
  45. ICML 2025PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering
  46. ICML 2025Provably Efficient Algorithm for Best Scoring Rule Identification in Online Principal-Agent Information Acquisition
  47. ICML 2025R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning
  48. ICML 2025Reidentify: Context-Aware Identity Generation for Contextual Multi-Agent Reinforcement Learning
  49. ICML 2025Reinforce LLM Reasoning through Multi-Agent Reflection
  50. ICML 2025ResearchTown: Simulator of Human Research Community

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