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 329 篇，第 2 / 7 页

51. ICLR 2024Learning to Jointly Understand Visual and Tactile Signals
52. ICLR 2024Lemur: Harmonizing Natural Language and Code for Language Agents
53. ICLR 2024Let Models Speak Ciphers: Multiagent Debate through Embeddings
54. ICLR 2024LOQA: Learning with Opponent Q-Learning Awareness
55. ICLR 2024LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents
56. ICLR 2024Maximum Entropy Heterogeneous-Agent Reinforcement Learning
57. ICLR 2024MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
58. ICLR 2024MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
59. ICLR 2024Modeling Boundedly Rational Agents with Latent Inference Budgets
60. ICLR 2024Neural Neighborhood Search for Multi-agent Path Finding
61. ICLR 2024On the Hardness of Constrained Cooperative Multi-Agent Reinforcement Learning
62. ICLR 2024Online Continual Learning for Interactive Instruction Following Agents
63. ICLR 2024PB-LLM: Partially Binarized Large Language Models
64. ICLR 2024Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning
65. ICLR 2024Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
66. ICLR 2024Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
67. ICLR 2024REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes
68. ICLR 2024Reward Design for Justifiable Sequential Decision-Making
69. ICLR 2024Sample-Efficient Multi-Agent RL: An Optimization Perspective
70. ICLR 2024Select to Perfect: Imitating desired behavior from large multi-agent data
71. ICLR 2024SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI Models
72. ICLR 2024SmartPlay : A Benchmark for LLMs as Intelligent Agents
73. ICLR 2024SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series
74. ICLR 2024Solving Homogeneous and Heterogeneous Cooperative Tasks with Greedy Sequential Execution
75. ICLR 2024SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents
76. ICLR 2024Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds
77. ICLR 2024Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
78. ICLR 2024The LLM Surgeon
79. ICLR 2024Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
80. ICLR 2024THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELS
81. ICLR 2024ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
82. ICLR 2024ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
83. ICLR 2024ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
84. ICLR 2024Towards Robust Multi-Modal Reasoning via Model Selection
85. ICLR 2024Trajeglish: Traffic Modeling as Next-Token Prediction
86. ICLR 2024Tree-Planner: Efficient Close-loop Task Planning with Large Language Models
87. ICLR 2024Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning
88. ICLR 2024Two-stage LLM Fine-tuning with Less Specialization and More Generalization
89. ICLR 2024Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions
90. ICLR 2024WebArena: A Realistic Web Environment for Building Autonomous Agents
91. ICLR 2024Whittle Index with Multiple Actions and State Constraint for Inventory Management
92. ICML 2024${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
93. ICML 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
94. ICML 2024Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment
95. ICML 2024Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
96. ICML 2024Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs
97. ICML 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls
98. ICML 2024ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL
99. ICML 2024Asymptotics of feature learning in two-layer networks after one gradient-step
100. ICML 2024BAGEL: Bootstrapping Agents by Guiding Exploration with Language

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。