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 178 篇，第 2 / 4 页

51. ICML 2025Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration
52. ICML 2025Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story
53. ICML 2025EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities
54. ICML 2025FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems
55. ICML 2025Fast Large Language Model Collaborative Decoding via Speculation
56. ICML 2025Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field Games
57. ICML 2025Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning
58. ICML 2025Fleet of Agents: Coordinated Problem Solving with Large Language Models
59. ICML 2025Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options
60. ICML 2025From Debate to Equilibrium: Belief‑Driven Multi‑Agent LLM Reasoning via Bayesian Nash Equilibrium
61. ICML 2025From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
62. ICML 2025G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks
63. ICML 2025General agents need world models
64. ICML 2025GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation
65. ICML 2025GradPS: Resolving Futile Neurons in Parameter Sharing Network for Multi-Agent Reinforcement Learning
66. ICML 2025Graph Diffusion for Robust Multi-Agent Coordination
67. ICML 2025Graph World Model
68. ICML 2025Gravity-Bench-v1: A Benchmark on Gravitational Physics Discovery for Agents
69. ICML 2025GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning
70. ICML 2025Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents
71. ICML 2025Hidden No More: Attacking and Defending Private Third-Party LLM Inference
72. ICML 2025Hybrid Quantum-Classical Multi-Agent Pathfinding
73. ICML 2025HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning
74. ICML 2025Improving Model Alignment Through Collective Intelligence of Open-Source Models
75. ICML 2025Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces
76. ICML 2025Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games
77. ICML 2025Investigating Non-Transitivity in LLM-as-a-Judge
78. ICML 2025ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks
79. ICML 2025KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems
80. ICML 2025KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search
81. ICML 2025Large Language Model-driven Large Neighborhood Search for Large-Scale MILP Problems
82. ICML 2025LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence
83. ICML 2025Learning Cascade Ranking as One Network
84. ICML 2025Learning Mean Field Control on Sparse Graphs
85. ICML 2025Learning Progress Driven Multi-Agent Curriculum
86. ICML 2025Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization
87. ICML 2025Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals
88. ICML 2025Learning to Stop: Deep Learning for Mean Field Optimal Stopping
89. ICML 2025Let LLM Tell What to Prune and How Much to Prune
90. ICML 2025Linear Contextual Bandits With Interference
91. ICML 2025LLM-Assisted Semantically Diverse Teammate Generation for Efficient Multi-agent Coordination
92. ICML 2025M³HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality
93. ICML 2025MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces
94. ICML 2025MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
95. ICML 2025MCU: An Evaluation Framework for Open-Ended Game Agents
96. ICML 2025MedRAX: Medical Reasoning Agent for Chest X-ray
97. ICML 2025MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
98. ICML 2025MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines
99. ICML 2025Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
100. ICML 2025MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking

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。