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 24 / 43 页

  1. ICML 2025Observation Interference in Partially Observable Assistance Games
  2. ICML 2025Offline Learning for Combinatorial Multi-armed Bandits
  3. ICML 2025On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents
  4. ICML 2025OrcaLoca: An LLM Agent Framework for Software Issue Localization
  5. ICML 2025Pairwise Maximum Likelihood For Multi-Class Logistic Regression Model With Multiple Rare Classes
  6. ICML 2025PokéChamp: an Expert-level Minimax Language Agent
  7. ICML 2025Position: Build Agent Advocates, Not Platform Agents
  8. ICML 2025Position: Theory of Mind Benchmarks are Broken for Large Language Models
  9. ICML 2025Position: Uncertainty Quantification Needs Reassessment for Large Language Model Agents
  10. ICML 2025Prediction-Aware Learning in Multi-Agent Systems
  11. ICML 2025Preference Controllable Reinforcement Learning with Advanced Multi-Objective Optimization
  12. ICML 2025Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents
  13. ICML 2025PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering
  14. ICML 2025Provably Efficient Algorithm for Best Scoring Rule Identification in Online Principal-Agent Information Acquisition
  15. ICML 2025R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning
  16. ICML 2025Reidentify: Context-Aware Identity Generation for Contextual Multi-Agent Reinforcement Learning
  17. ICML 2025Reinforce LLM Reasoning through Multi-Agent Reflection
  18. ICML 2025ResearchTown: Simulator of Human Research Community
  19. ICML 2025Revisiting Cooperative Off-Policy Multi-Agent Reinforcement Learning
  20. ICML 2025Robust Multi-Agent Reinforcement Learning with Stochastic Adversary
  21. ICML 2025Sable: a Performant, Efficient and Scalable Sequence Model for MARL
  22. ICML 2025Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games
  23. ICML 2025SHIELD: Multi-task Multi-distribution Vehicle Routing Solver with Sparsity and Hierarchy
  24. ICML 2025Super Deep Contrastive Information Bottleneck for Multi-modal Clustering
  25. ICML 2025Synthesizing Software Engineering Data in a Test-Driven Manner
  26. ICML 2025The impact of uncertainty on regularized learning in games
  27. ICML 2025Tight and Fast Bounds for Multi-Label Learning
  28. ICML 2025Towards Practical Defect-Focused Automated Code Review
  29. ICML 2025Towards the Causal Complete Cause of Multi-Modal Representation Learning
  30. ICML 2025Training a Generally Curious Agent
  31. ICML 2025Understanding Bias Reinforcement in LLM Agents Debate
  32. ICML 2025Unisoma: A Unified Transformer-based Solver for Multi-Solid Systems
  33. ICML 2025What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities
  34. ICML 2025Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
  35. ICML 2025Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
  36. ICML 2025Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning
  37. ICML 2025You Always Recognize Me (YARM): Robust Texture Synthesis Against Multi-View Corruption
  38. NeurIPS 2025$i$MIND: Insightful Multi-subject Invariant Neural Decoding
  39. NeurIPS 20253DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
  40. NeurIPS 2025A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
  41. NeurIPS 2025A machine learning approach that beats Rubik's cubes
  42. NeurIPS 2025A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond
  43. NeurIPS 2025A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
  44. NeurIPS 2025Adaptive and Multi-scale Affinity Alignment for Hierarchical Contrastive Learning
  45. NeurIPS 2025Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning
  46. NeurIPS 2025Aeolus: A Multi-structural Flight Delay Dataset
  47. NeurIPS 2025AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement
  48. NeurIPS 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
  49. NeurIPS 2025AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks
  50. NeurIPS 2025Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-Index Models

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