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 868 篇，第 14 / 18 页

  1. NeurIPS 2026FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration
  2. NeurIPS 2026FlashFFN: Multi-Head Decomposition Enables I/O-Aware Feed-Forward Network
  3. NeurIPS 2026FlowLeak: Coverage-Guided Extraction of Dynamic Workflows in LLM-Based Multi-Agent Systems
  4. NeurIPS 2026FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
  5. NeurIPS 2026FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics
  6. NeurIPS 2026Focusing Influence Mechanism for Multi-Agent Reinforcement Learning
  7. NeurIPS 2026Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap
  8. NeurIPS 2026Frequency-Structured Hamiltonian Neural Network for Multi-Timescale Dynamics
  9. NeurIPS 2026From Chats to Markets: AgenticPay for LLM-Powered Negotiation in Multi-Agent Commerce
  10. NeurIPS 2026From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
  11. NeurIPS 2026From Talking Words to Sharing Thoughts: Scalable Multi-LLM Aggregation via Structured Message Passing
  12. NeurIPS 2026Generalized Intention Modeling in Multi-Agent Reinforcement Learning
  13. NeurIPS 2026Grounding Agent Reasoning with Structured Process Supervision for Multi-turn Reinforcement Learning
  14. NeurIPS 2026Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
  15. NeurIPS 2026Group Perspective Matters: Regulating Debate Relationships Can Mitigate Blind Conformity in Multi-Agent Debate
  16. NeurIPS 2026GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations
  17. NeurIPS 2026HAI: Hierarchical Anchored Interaction for Multi-View Bimanual World Models
  18. NeurIPS 2026Hermes: A Multi-Scale Spatial-Temporal Hypergraph Network for Stock Time Series Forecasting
  19. NeurIPS 2026Heterogeneous Agent Collaborative Reinforcement Learning
  20. NeurIPS 2026How LLMs Distinguish Threats from Offers
  21. NeurIPS 2026How to Interpret Agent Behavior
  22. NeurIPS 2026HyperSkill: Multi-Modal Skill Learning on the Unit Hypersphere
  23. NeurIPS 2026Implicit Value Probing: Inferring Human Value Preferences via Strategic Multi-Turn Conversations
  24. NeurIPS 2026Improved Sample Complexity for Markov Games via Variance-Aware Bandit Learning
  25. NeurIPS 2026Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics
  26. NeurIPS 2026Individuals Matter: Improving Deep Multi-View Clustering via Explicit Single-View Enhancement
  27. NeurIPS 2026InfoFlow: A Framework for Multi-Layer Transformer Analysis
  28. NeurIPS 2026Integrating Strengths of Different Multi-Agent Workflows via Step-Aware Hybrid Topology Planning
  29. NeurIPS 2026Inter-Agent Influence: Evaluating Persuasion, Deception and Coercion in Multi-Agent Systems
  30. NeurIPS 2026Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)
  31. NeurIPS 2026Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs
  32. NeurIPS 2026Jacobian Descent for Multi-Objective Optimization
  33. NeurIPS 2026Know Your Task, Learn It Right: Task-Aware Optimistic Value Learning for Multi-Task Multi-Agent Reinforcement Learning
  34. NeurIPS 2026KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling
  35. NeurIPS 2026Language-Based Agent Control
  36. NeurIPS 2026LDPCache: Locally Differentially Private Multi-Query Processing with Cache Optimization for Large Language Models
  37. NeurIPS 2026Learning in Causal Markov Games
  38. NeurIPS 2026Learning Large-Scale Competitive Team Behaviors with Mean-Field Interactions
  39. NeurIPS 2026Learning Orthogonal Multi-Index Models Beyond Small Initialization: Incremental Learning, Competitive Dynamics and Symmetry
  40. NeurIPS 2026Learning When to Collaborate: Selective Multi-Agent Medical Reasoning via Uncertainty-Aware Routing
  41. NeurIPS 2026LLM-Based Multi-Agent Blackboard System for Information Discovery in Data Science
  42. NeurIPS 2026LogSig-SSM: Time-Series Modelling with Multi-Scale Log-Signature Compression for State-Space Models
  43. NeurIPS 2026LongMINT: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
  44. NeurIPS 2026LoRASpace: A Pool-Wide Shared Substrate for Static and Dynamic Multi-LoRA Composition
  45. NeurIPS 2026MACRO: Training-free Multi-plane Attention for Closeup Render Optimization
  46. NeurIPS 2026MAGE: Towards Generalizable Multi-timescale EEG Representations
  47. NeurIPS 2026MANGO:Multi-Angle Neural Gated Operators for Chirp-Perturbed PDEs
  48. NeurIPS 2026MARBLE: an Agent Benchmark for Spatial Reasoning and Visual Abstraction
  49. NeurIPS 2026MaRiO: Multi-agent Collaborative Reasoning via Shared Observations in MLLMs
  50. NeurIPS 2026Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems

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