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 10 / 43 页

  1. ICML 2026LEGO: An LLM-Enabled Hierarchical Optimizer for Tensor Computation Graphs with Structure-Aware Search and Compositional Synthesis
  2. ICML 2026Let the Prototype Guide You: Robust Aggregation of Sparse Multi-Class Annotations via Annotator Prototype Learning
  3. ICML 2026LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior
  4. ICML 2026LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning
  5. ICML 2026LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents
  6. ICML 2026LS$^{2}$MC-GDA: A Smoothed Algorithm for Federated Stochastic Multi-Level Compositional Minimax Optimization
  7. ICML 2026MaMa: A Game-Theoretic Approach for Designing Safe Agentic Systems
  8. ICML 2026MARS-SQL: A Multi-Agent Reinforcement Learning Framework For Text-To-SQL
  9. ICML 2026MARS: Modular Agent with Reflective Search for Automated AI Research
  10. ICML 2026MAS-Architect: Declarative Multi-Agent System Design via Separation of Concerns
  11. ICML 2026MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems
  12. ICML 2026MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
  13. ICML 2026MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks
  14. ICML 2026MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning
  15. ICML 2026MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games
  16. ICML 2026MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering
  17. ICML 2026Meta-Black-Box Optimization Can Do Search Guidance for Expensive Constrained Multi-Objective Optimization
  18. ICML 2026MIMO-LP: A Multi-Input Multi-Output Framework for Subgraph-based Link Prediction
  19. ICML 2026MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation
  20. ICML 2026Mitigating Conversational Inertia in Multi-Turn Agents
  21. ICML 2026ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering
  22. ICML 2026MOC: Multi-Order Communication in LLM-based Multi-Agent Systems
  23. ICML 2026MonoScale: Scaling Multi-Agent System with Monotonic Improvement
  24. ICML 2026Mosaic: Runtime-Efficient Multi-Agent Embodied Planning
  25. ICML 2026MulFCoder: Framework-conditioned Multi-agent for MLLM-based Multi-framework Front-end Code Generation
  26. ICML 2026Multi-Adapter Representation Interventions via Energy Calibration
  27. ICML 2026Multi-agent imitation learning with function approximation: linear Markov games and beyond
  28. ICML 2026Multi-Agent Reinforcement Learning with Submodular Reward
  29. ICML 2026Multi-Agent Teams Hold Experts Back
  30. ICML 2026Multi-Distribution Robust Conformal Prediction
  31. ICML 2026Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamics
  32. ICML 2026Multi-marginal temporal Schrödinger Bridge Matching from unpaired data
  33. ICML 2026Multi-scale Explainer for Graph Neural Networks
  34. ICML 2026Multi-Task Bayesian In-Context Learning
  35. ICML 2026Multi-timescale Reinforcement Learning by Value Reconstruction
  36. ICML 2026Multi-view Consistent Latent Action Learning for World Modeling and Control
  37. ICML 2026Multi-Way Representation Alignment
  38. ICML 2026Narrowing the ANN–SNN Gap for Continuous 1D Temporal Signal Classification with Multi-Scale Temporal Encoding and Sparsity-Regularized Transform Encoding
  39. ICML 2026Near-Optimal Regret for KL-Regularized Multi-Armed Bandits
  40. ICML 2026Not All Prefills Are Equal: PPD Disaggregation for Multi-turn LLM Serving
  41. ICML 2026Offline Multi-agent Continual Cooperation via Skill Partition and Reuse
  42. ICML 2026Offline Two-Player Zero-Sum Markov Games with KL Regularization
  43. ICML 2026OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration
  44. ICML 2026On Effectiveness and Efficiency of Agentic Tool-calling and RL Training
  45. ICML 2026One Coin Has Two Sides: Single Poistive Multi Label Learning from Salient Annotations
  46. ICML 2026Online Linear Programming for Multi-Objective Routing in LLM Serving
  47. ICML 2026Optimal and Scalable MAPF via Multi-Marginal Optimal Transport and Schrödinger Bridges
  48. ICML 2026Optimal Rates for Feasible Payoff Set Estimation in Games
  49. ICML 2026PhenoBrain: Phenotype-Conditioned Long-Range Communication for Multi-Modal Brain Network Analysis
  50. ICML 2026Population-Free Pareto Tracking for Sample-Efficient Multi-Policy MORL

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