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 16 / 43 页

  1. NeurIPS 2026ORCA: Orthogonal Residual Consensus Alignment for Multi-View Clustering
  2. NeurIPS 2026OrchestraRL: Learning to Orchestrate LLM Agent Swarms with Entropy-Aware Communication Control
  3. NeurIPS 2026Outbidding and Outbluffing Elite Humans: Mastering Liar’s Poker via Self-Play and Reinforcement Learning
  4. NeurIPS 2026Outlier-Robust Multi-Output Gaussian Processes
  5. NeurIPS 2026Overcoming Attention Distraction: Training-Free Latent Communication for Multi-Agent Systems
  6. NeurIPS 2026PAI-Actor: Cinematic Multi-Actor Character Replacement in Dynamic Scenes
  7. NeurIPS 2026PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
  8. NeurIPS 2026Permutation Sensitivity in t-SVD-based Multi-view Clustering
  9. NeurIPS 2026PHOEBI: An Open-World Benchmark for Multi-Label Bacterial Identification in Phase-Contrast Microscopy
  10. NeurIPS 2026PhyMo: Learning Physical Dynamics with Accurate and Continuous Motion from Multi-View Videos
  11. NeurIPS 2026Physical AI Smart Spaces: A Large-Scale Benchmark for Multi-Camera 3D Perception in Smart Spaces
  12. NeurIPS 2026PithTrain: A Compact and Agent-Native MoE Training System
  13. NeurIPS 2026PLATO: Pointer Learner for Agent and Task Openness
  14. NeurIPS 2026Playing Markov Games Without Observing Payoffs
  15. NeurIPS 2026Policy Regret Minimization in Partially Observable Markov Games
  16. NeurIPS 2026Policy-Level Exploration for Coordinated Multi-Agent Reinforcement Learning
  17. NeurIPS 2026Position: A Safe LLM and a Safe Harness Do Not Make a Safe Agent
  18. NeurIPS 2026Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning
  19. NeurIPS 2026PREPING: Building Agent Memory without Tasks
  20. NeurIPS 2026Programmatic Reasoning with Structural Schema: A Unified Framework for Multi-Table Inference
  21. NeurIPS 2026PurpleAudit: A Co-Evolutionary Auditing Framework for Task Hijacking in Multi-Agent Systems
  22. NeurIPS 2026QDMouse4M: A Multi-View 3D Mouse Spontaneous Behavior Dataset with Quantum-Dot Markers
  23. NeurIPS 2026Quality-Diversity Optimization as Multi-Objective Optimization
  24. NeurIPS 2026Quantum Speedup of Multi-armed Bandits at Scale by Tackling Memory Decoherence
  25. NeurIPS 2026RADAR: Routing Agents via Difficulty-Aware Recovery
  26. NeurIPS 2026Rare Disease Diagnosis Agent with Decoupled Workflows and Knowledge-Driven Self-Evaluation
  27. NeurIPS 2026Recursive Multi-Agent Systems
  28. NeurIPS 2026Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching
  29. NeurIPS 2026Releasing Anchors from Cross-View Correspondence: Probabilistic Multi-View Anchor Graph Clustering
  30. NeurIPS 2026Reliable Federated Multi-View Learning via Conflict-Aware Evidence Calibration
  31. NeurIPS 2026Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
  32. NeurIPS 2026Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
  33. NeurIPS 2026Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning
  34. NeurIPS 2026Reward Modeling for Multi-Agent Orchestration
  35. NeurIPS 2026RIGOR: Risk-Gated Topology Adaptation for Robust LLM Multi-Agent Reasoning
  36. NeurIPS 2026RipBench: A Unified Benchmark for Multi-Level Rip Current Detection, Classification and Segmentation
  37. NeurIPS 2026Risk-Calibrated Context Selection for Healthcare Multi-Agent Handoff
  38. NeurIPS 2026Robust Multi-view Clustering against Imperfect Information
  39. NeurIPS 2026ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork
  40. NeurIPS 2026RuleSmith: Multi-Agent LLMs for Automated Game Balancing
  41. NeurIPS 2026Runtime Verification of Multiple Natural Language Criteria for Agent Governance
  42. NeurIPS 2026S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields
  43. NeurIPS 2026Safe-Fair MACPO: Burden-Fair Constrained Policy Optimization for Safe Multi-Agent Reinforcement Learning
  44. NeurIPS 2026SAIR: Cost-Efficient Multi-Stage ML Pipeline Autoscaling via In-Context Reinforcement Learning
  45. NeurIPS 2026Saliency-Aware Multi-Route Thinking: Grounding and Reasoning on Vision-Language Agents
  46. NeurIPS 2026Scaffold3D: SfM-Conditioned Pointmap Prediction for Multi-View 3D Reconstruction
  47. NeurIPS 2026Scalable Multi-Agent Contrastive Reinforcement Learning
  48. NeurIPS 2026SCHOLARPEER: A Multi-Agent Framework for Automated Peer Review
  49. NeurIPS 2026SCOT: Multi-Source Cross-City Transfer with Optimal-Transport Soft-Correspondence Objectives
  50. NeurIPS 2026SeaPilot: Mobile Agent with Self-refining Environment Alignment

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