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 18 / 43 页

  1. NeurIPS 2026VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
  2. NeurIPS 2026VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning
  3. NeurIPS 2026Wayfinder: Adaptive Resource Routing from Agent Citations
  4. NeurIPS 2026Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation
  5. NeurIPS 2026What Makes Two States the Same? Value-Aware State Matching for Multi-Turn Agent Credit Assignment
  6. NeurIPS 2026When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?
  7. NeurIPS 2026When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning
  8. NeurIPS 2026When Do Multi-Agent Systems Help? An Information Bottleneck Perspective
  9. NeurIPS 2026When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding
  10. NeurIPS 2026When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory
  11. NeurIPS 2026When the Most Disruptive Messages Are Safe to Prune in Aggregate: Functional Analysis of Communication Pruning in Two-Agent LLM Systems
  12. NeurIPS 2026Who Should Evolve? Uncertainty-Aware Role Bottleneck Inference for Multi-Agent LLM Training
  13. NeurIPS 2026Why Copy Others? Insights into Social Learning from Multi-Agent Reinforcement Learning
  14. NeurIPS 2026WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction
  15. NeurIPS 2026WURI: Watching Unfolding Risk in Agent Interactions
  16. NeurIPS 2026Youdunit: Single-Call Counterfactual Necessity in Multi-Agent LLM Systems
  17. NeurIPS 2026Zero-Violation Regret for Cooperative Markov Games with Coupled Instantaneous Hard Constraints
  18. NeurIPS 2026Zeroth-Order Stackelberg Control in Combinatorial Congestion Games
  19. CVPR 20253D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer
  20. CVPR 20253DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement
  21. CVPR 2025A Hubness Perspective on Representation Learning for Graph-Based Multi-View Clustering
  22. CVPR 2025AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments
  23. CVPR 2025All-Day Multi-Camera Multi-Target Tracking
  24. CVPR 2025ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding
  25. CVPR 2025ATA: Adaptive Transformation Agent for Text-Guided Subject-Position Variable Background Inpainting
  26. CVPR 2025Attribute-Missing Multi-view Graph Clustering
  27. CVPR 2025BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
  28. CVPR 2025CaMuViD: Calibration-Free Multi-View Detection
  29. CVPR 2025CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models
  30. CVPR 2025CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools
  31. CVPR 2025Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification
  32. CVPR 2025ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinate
  33. CVPR 2025CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation
  34. CVPR 2025CLOC: Contrastive Learning for Ordinal Classification with Multi-Margin N-pair Loss
  35. CVPR 2025CocoER: Aligning Multi-Level Feature by Competition and Coordination for Emotion Recognition
  36. CVPR 2025Collaborative Tree Search for Enhancing Embodied Multi-Agent Collaboration
  37. CVPR 2025CoMatcher: Multi-View Collaborative Feature Matching
  38. CVPR 2025Compositional Targeted Multi-Label Universal Perturbations
  39. CVPR 2025CorrBEV: Multi-View 3D Object Detection by Correlation Learning with Multi-modal Prototypes
  40. CVPR 2025Correlative and Discriminative Label Grouping for Multi-Label Visual Prompt Tuning
  41. CVPR 2025Cross-Modal 3D Representation with Multi-View Images and Point Clouds
  42. CVPR 2025Deep Fair Multi-View Clustering with Attention KAN
  43. CVPR 2025Detect Any Mirrors: Boosting Learning Reliability on Large-Scale Unlabeled Data with an Iterative Data Engine
  44. CVPR 2025DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer
  45. CVPR 2025Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
  46. CVPR 2025DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling
  47. CVPR 2025EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues
  48. CVPR 2025Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input
  49. CVPR 2025EgoLM: Multi-Modal Language Model of Egocentric Motions
  50. CVPR 2025Enhanced then Progressive Fusion with View Graph for Multi-View Clustering

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