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 868 篇，第 9 / 18 页

  1. ICML 2026EvoMAS: Heuristics in the Loop—Evolving Smarter Agentic Workflows
  2. ICML 2026Executable Agentic Memory for GUI Agent
  3. ICML 2026Exploration-free Algorithms for Multi-group Mean Estimation
  4. ICML 2026Factored Value Functions for Graph-Based Multi-Agent Reinforcement Learning
  5. ICML 2026Fast and Expressive Multi-Byte Prediction with Probabilistic Circuits
  6. ICML 2026Federated Causal Inference on Multi-Site Observational Data via Propensity Score Aggregation
  7. ICML 2026Federated Multi-view Clustering for Remote Sensing Data
  8. ICML 2026FiGuRO: Intrinsic Dimension Estimation for Multi-Modal Data
  9. ICML 2026Fine-to-Coarse Fairness-Informed Multi-View Clustering
  10. ICML 2026FIRE: Multi-Fidelity Regression with Distribution-Conditioned In-Context Learning Using Tabular Foundation Models
  11. ICML 2026Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors
  12. ICML 2026FlowMAP: Flow Matching for Generalizable Agent Planning
  13. ICML 2026Focus and Dilution: The Multi-stage Learning Process of Attention
  14. ICML 2026From Interaction Trajectories to Prompt Rules: Credit Assignment for Multi-Agent Prompt Optimization
  15. ICML 2026FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation
  16. ICML 2026GameDevBench: Evaluating Agentic Capabilities Through Game Development
  17. ICML 2026GFD-EMVC: Evolutionary Multi-View Classification with Label Noise via Gradient and Feature Dual-Perception
  18. ICML 2026GLEAN: Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification
  19. ICML 2026Gradient Descent with Large Step Size Restores Symmetry in Deep Linear Networks with Multi-Pathway
  20. ICML 2026Great Minds Think Alike: Contextual Tacit Communication for Decentralized LLM-Agent Cooperation
  21. ICML 2026GRPO-based Cluster Decision Agent for Unknown-$\boldsymbol{K}$ Multi-view Clustering
  22. ICML 2026HieraMAS: Optimizing Intra-Node LLM Mixtures and Inter-Node Topology for Multi-Agent Systems
  23. ICML 2026Hierarchical Anchor Graph Learning for Multi-View Clustering
  24. ICML 2026Hierarchical Multi Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation
  25. ICML 2026HiMAP-Travel: Hierarchical Multi-Agent Planning for Long-Horizon Constrained Travel
  26. ICML 2026HiPER: Hierarchical Plan–Execute RL for Multi-Turn LLM Agents
  27. ICML 2026How Far Can LLM Agents Reason with Tables? Benchmarking Multi-Turn Agentic Table Question Answering in the Wild
  28. ICML 2026HPS: Hyperspherical Parameter Sharing for Efficient Multi-Agent Reinforcement Learning
  29. ICML 2026HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation
  30. ICML 2026Identifying dependent components from multi-domain linear mixtures
  31. ICML 2026IEC: When Information-Driven Exploration Meets Spectral Consensus via Primal–Dual Reward Regularization in Decentralized Multi-Agent RL
  32. ICML 2026Inference from Quantized Data via Normal Variance-Mean Mixtures
  33. ICML 2026InfoPO: Information-Driven Policy Optimization for User-Centric Agents
  34. ICML 2026InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem
  35. ICML 2026Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning
  36. ICML 2026Investigating Component Contributions in Multi-Agent ML Systems
  37. ICML 2026JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG
  38. ICML 2026Judgment Operators: A Composition-Invariant Substrate for Multi-Agent Action Spaces
  39. ICML 2026Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs
  40. ICML 2026KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed Bandits
  41. ICML 2026Knothe-Rosenblatt Quantile Regression for Risk-sensitive Multi-objective Reinforcement Learning
  42. ICML 2026Large Language Model Agents Are Not Always Faithful Self-Evolvers
  43. ICML 2026Latent Collaboration in Multi-Agent Systems
  44. ICML 2026Learn to change the world: Multi-level reinforcement learning with model-changing actions
  45. ICML 2026Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic
  46. ICML 2026Learning Generalized Label Distributions
  47. ICML 2026Learning Multi-Agent Coordination via Sheaf-ADMM
  48. ICML 2026Learning Multi-Scale Hypergraph for High-Order Brain Connectivity Analysis
  49. ICML 2026Learning Robust Multi-Agent Policies via Selective Adversarial Fault Induction
  50. ICML 2026Learning to Share: Selective Memory for Efficient Parallel Agentic Systems

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