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 809 篇，第 4 / 17 页

  1. NeurIPS 2026Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems
  2. NeurIPS 2026Market-Based Runtime Resource Allocation for LLM Multi-Agent Systems
  3. NeurIPS 2026MASTARS: Multi-Agent Sequential Trajectory Augmentation with Return-Conditioned Subgoals
  4. NeurIPS 2026MC-H: Multi-Granularity Clustering with Hyperspherical Determinantal Point Process
  5. NeurIPS 2026MC$^2$Mark: Distortion-Free Multi-Bit Watermarking for Long Messages
  6. NeurIPS 2026MCAS: Signal-Processing-Based Multi-View Contrastive Learning for Acoustic Sensing
  7. NeurIPS 2026MemContract: Contract-Sensitive Evaluation for Mutable Agent Memory
  8. NeurIPS 2026MEME: Multi-Entity & Evolving Memory Evaluation
  9. NeurIPS 2026MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging
  10. NeurIPS 2026Mental-Models for Multi-Agent Systems
  11. NeurIPS 2026MGMem: An Efficient, Deterministic, and Provenance-Preserving Framework for Long-Horizon Agent Memory
  12. NeurIPS 2026MHWA: Multi-timescale Hierarchical World-Action Model
  13. NeurIPS 2026MICE: Multi-animal Interaction Context Encoder — A Hierarchical Foundation Model for Mouse Behavior
  14. NeurIPS 2026MindGames:A Multi-Agent Benchmark and Trajectory Dataset for Evaluating Social and Strategic Reasoning in LLMs
  15. NeurIPS 2026MindGuard: Guardrail Classifiers for Multi-Turn Mental Health Support
  16. NeurIPS 2026Mitigating Retaliatory Algorithmic Collusion in Repeated Games
  17. NeurIPS 2026MMA-SafetyBench: A Benchmark for Multimodal Agent Safety Evaluation
  18. NeurIPS 2026Modelling Opinion Dynamics at Scale with Deep MARL
  19. NeurIPS 2026Monotone Inclusion Approach to Weakly Monotone Discrete-Time Finite-Horizon Mean-Field Games
  20. NeurIPS 2026MotionGrounder: Grounded Multi-Object Motion Transfer via Diffusion Transformer
  21. NeurIPS 2026MSAR: Next-Scale Autoregressive Forecasting for Time Series via Modular Multi-Scale Decoupling
  22. NeurIPS 2026MSR-3D: Multi-Mode Semantic Representation for Open-Vocabulary 3D Scene Understanding
  23. NeurIPS 2026Multi-agent Collaboration with State Management
  24. NeurIPS 2026Multi-Agent Coordination via Support-Preserving Distillation
  25. NeurIPS 2026Multi-Armed Bandits With Best-Action Queries
  26. NeurIPS 2026Multi-Constrained Randomized Smoothing Certificates
  27. NeurIPS 2026Multi-Environment POMDPs with Finite-Horizon Objectives
  28. NeurIPS 2026Multi-Nonsmooth-Nonconvex-Objective Optimization
  29. NeurIPS 2026Multi-site PPG: An In-the-Wild Physiological Dataset from Emerging Multi-Site Wearables
  30. NeurIPS 2026Multi-Stage Planning from Single-Stage Data: Reinforcement Learning Helps Composition but Requires Anchoring
  31. NeurIPS 2026Multi-step Consistency Models: A Complete Error Theory and Optimal Step Selection
  32. NeurIPS 2026Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards
  33. NeurIPS 2026Multi-Variable Conformal Prediction: Optimizing Prediction Sets without Data Splitting
  34. NeurIPS 2026MUSS: A Multi-scale and Sequence-based Model for Single-cell Gene Regulation
  35. NeurIPS 2026MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction
  36. NeurIPS 2026NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis
  37. NeurIPS 2026Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret
  38. NeurIPS 2026Near-Optimal Best-of-Both-Worlds Algorithms for Decoupled Exploration and Exploitation in Multi-armed Bandits
  39. NeurIPS 2026Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions
  40. NeurIPS 2026Near-Optimal Stochastic Linear Bandits with Delay
  41. NeurIPS 2026Network Intervention by Polling Strategic Agents
  42. NeurIPS 2026Noise-Level KL Rates for Multi-Marginal Schrödinger Bridge Surrogates
  43. NeurIPS 2026Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems
  44. NeurIPS 2026OmniMemBench: Towards Scalable Evaluation of Long-Term Omni-Modal Agent Memory
  45. NeurIPS 2026On the Impact of Side-Information in Bandit Learning: More is Not Always Merrier
  46. NeurIPS 2026On the Information Loss of Multi-Token Prediction: Origin and Solution
  47. NeurIPS 2026On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization
  48. NeurIPS 2026OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories
  49. NeurIPS 2026Optimal scaling laws in learning hierarchical multi-index models
  50. NeurIPS 2026Optimize Once, Execute Fast: Latency-Aware Multi-Agent Workflow Learning for Recurrent Queries

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