AI 智能体论文趋势 2023–2026

主要结论

• AI 智能体论文从 2023 年的 170 篇增长到 2026 年的 1,983 篇，三年间扩大到约 12 倍。
• NeurIPS 是发AI 智能体论文最多的会议，2023–2026 年共 1,317 篇，占四个会议总量的 40%。
• 交叉方向里涨得最快的是大模型基准：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 116 篇。
• 在「前沿系统」的 4 个主题里，它的 2026 年论文数排第 2；同组增长最快的世界模型是 11 倍，AI 智能体是 12 倍。

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

• NeurIPS 2026$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
• ICML 2026$\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge
• ICLR 2026A Benchmark for Deep Information Synthesis
• CVPR 20263D-VCD Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive
• NeurIPS 20254KAgent: Agentic Any Image to 4K Super-Resolution
• ICML 2025A Unified Approach to Routing and Cascading for LLMs
• ICLR 2025A Generalist Hanabi Agent
• CVPR 2025Collaborative Tree Search for Enhancing Embodied Multi-Agent Collaboration
• NeurIPS 2024AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making
• ICML 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
• ICLR 2024A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
• CVPR 2024Density-Adaptive Model Based on Motif Matrix for Multi-Agent Trajectory Prediction
• NeurIPS 2023AdaPlanner: Adaptive Planning from Feedback with Language Models
• ICML 2023A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems
• ICLR 2023Achieving Near-Optimal Individual Regret & Low Communications in Multi-Agent Bandits
• CVPR 2023Behavioral Analysis of Vision-and-Language Navigation Agents
• NeurIPS 20262-Step Agent: How a Bayesian Decision Maker Learns from AI-Decision Support
• ICML 2026$\tau$-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains
• ICLR 2026A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments
• CVPR 2026A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoning

全部AI 智能体论文

共 170 篇，第 1 / 4 页

1. CVPR 2023Behavioral Analysis of Vision-and-Language Navigation Agents
2. CVPR 2023Collaboration Helps Camera Overtake LiDAR in 3D Detection
3. CVPR 2023D2Former: Jointly Learning Hierarchical Detectors and Contextual Descriptors via Agent-Based Transformers
4. CVPR 2023EqMotion: Equivariant Multi-Agent Motion Prediction With Invariant Interaction Reasoning
5. CVPR 2023FJMP: Factorized Joint Multi-Agent Motion Prediction Over Learned Directed Acyclic Interaction Graphs
6. CVPR 2023IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction
7. CVPR 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction Using Diffusion
8. CVPR 2023Multi-Agent Automated Machine Learning
9. CVPR 2023PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation
10. CVPR 2023Query-Centric Trajectory Prediction
11. CVPR 2023Revisiting the P3P Problem
12. CVPR 2023StarCraftImage: A Dataset for Prototyping Spatial Reasoning Methods for Multi-Agent Environments
13. CVPR 2023ViP3D: End-to-End Visual Trajectory Prediction via 3D Agent Queries
14. ICLR 2023$O(T^{-1})$ Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games
15. ICLR 2023Achieving Near-Optimal Individual Regret & Low Communications in Multi-Agent Bandits
16. ICLR 2023Adversarial Diversity in Hanabi
17. ICLR 2023Asynchronous Gradient Play in Zero-Sum Multi-agent Games
18. ICLR 2023Broken Neural Scaling Laws
19. ICLR 2023Can We Find Nash Equilibria at a Linear Rate in Markov Games?
20. ICLR 2023Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication
21. ICLR 2023Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning
22. ICLR 2023Collaborative Pure Exploration in Kernel Bandit
23. ICLR 2023Competitive Physics Informed Networks
24. ICLR 2023Discovering Generalizable Multi-agent Coordination Skills from Multi-task Offline Data
25. ICLR 2023Does Zero-Shot Reinforcement Learning Exist?
26. ICLR 2023Efficiently Computing Nash Equilibria in Adversarial Team Markov Games
27. ICLR 2023Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games
28. ICLR 2023Generating Diverse Cooperative Agents by Learning Incompatible Policies
29. ICLR 2023GoBigger: A Scalable Platform for Cooperative-Competitive Multi-Agent Interactive Simulation
30. ICLR 2023Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent
31. ICLR 2023Learning Rationalizable Equilibria in Multiplayer Games
32. ICLR 2023Learning to Extrapolate: A Transductive Approach
33. ICLR 2023Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased
34. ICLR 2023MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection
35. ICLR 2023MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
36. ICLR 2023Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning
37. ICLR 2023Minimax Optimal Kernel Operator Learning via Multilevel Training
38. ICLR 2023More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization
39. ICLR 2023Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication
40. ICLR 2023Offline Congestion Games: How Feedback Type Affects Data Coverage Requirement
41. ICLR 2023Order Matters: Agent-by-agent Policy Optimization
42. ICLR 2023Proactive Multi-Camera Collaboration for 3D Human Pose Estimation
43. ICLR 2023ReAct: Synergizing Reasoning and Acting in Language Models
44. ICLR 2023Representation Learning for Low-rank General-sum Markov Games
45. ICLR 2023Revisiting Populations in multi-agent Communication
46. ICLR 2023RPM: Generalizable Multi-Agent Policies for Multi-Agent Reinforcement Learning
47. ICLR 2023Scaling Laws for a Multi-Agent Reinforcement Learning Model
48. ICLR 2023Solving Continuous Control via Q-learning
49. ICLR 2023Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
50. ICLR 2023Taking a Step Back with KCal: Multi-Class Kernel-Based Calibration for Deep Neural Networks

常见问题

2023–2026 年四大会议一共有多少篇AI 智能体论文？

共 3,266 篇，按年份分别是 2023 年 170 篇、2024 年 329 篇、2025 年 784 篇、2026 年 1,983 篇。

NeurIPS 2026 有多少篇AI 智能体论文？

NeurIPS 2026 有 729 篇AI 智能体论文，上一届是 362 篇。

ICLR 2026 有多少篇AI 智能体论文？

ICLR 2026 有 500 篇AI 智能体论文，上一届是 204 篇。

ICML 2026 有多少篇AI 智能体论文？

ICML 2026 有 640 篇AI 智能体论文，上一届是 178 篇。

CVPR 2026 有多少篇AI 智能体论文？

CVPR 2026 有 114 篇AI 智能体论文，上一届是 40 篇。

哪个会议的AI 智能体论文最多？

NeurIPS，2023–2026 年共 1,317 篇。