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 3,266 篇，第 3 / 66 页

101. CVPR 2026ViBES A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body
102. CVPR 2026VideoARM Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding
103. CVPR 2026VideoChat-M1 Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement
104. CVPR 2026VideoSeek Long-Horizon Video Agent with Tool-Guided Seeking
105. CVPR 2026VideoWeaver Multimodal Multi-View Video-to-Video Transfer for Embodied Agents
106. CVPR 2026ViLoMem Agentic Learner with Grow-and-Refine Multimodal Semantic Memory
107. CVPR 2026Vinedresser3D Towards Agentic Text-guided 3D Editing
108. CVPR 2026VISTA A Test-Time Self-Improving Video Generation Agent
109. CVPR 2026Visual Document Understanding and Reasoning A Multi-Agent Collaboration Framework with
110. CVPR 2026VQ-VA World Towards High-Quality Visual Question-Visual Answering
111. CVPR 2026VS-Bench Evaluating VLMs for Strategic Abilities in Multi-Agent Environments
112. CVPR 2026VULCAN Tool-Augmented Multi Agents for Iterative 3D Object Arrangement
113. CVPR 2026When Robots Should Say I Dont Know Benchmarking Abstention in
114. CVPR 2026YoCity Personalized and Boundless 3D Realistic City Scene Generation via
115. ICLR 2026$p\textrm{-less}$ Sampling: A Robust Hyperparameter-Free Approach for LLM Decoding
116. ICLR 2026A Benchmark for Deep Information Synthesis
117. ICLR 2026A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA
118. ICLR 2026A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments
119. ICLR 2026A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning
120. ICLR 2026A$^2$Search: Ambiguity-Aware Question Answering with Reinforcement Learning
121. ICLR 2026A2ASecBench: A Protocol-Aware Security Benchmark for Agent-to-Agent Multi-Agent Systems
122. ICLR 2026ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems
123. ICLR 2026Achieving Expert-Level Agent from Foundation Model via Complexity Curriculum Reinforcement Learning with Synthetic Data
124. ICLR 2026Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
125. ICLR 2026Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning
126. ICLR 2026Advancing Multi-agent Traffic Simulation via R1-Style Reinforcement Fine-Tuning
127. ICLR 2026Aegis: Automated Error Generation and Identification for Multi-Agent Systems
128. ICLR 2026AesCoder: Code Aesthetics with Agentic Reward Feedback
129. ICLR 2026Agent Data Protocol
130. ICLR 2026Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks
131. ICLR 2026AgentFold: Long-Horizon Web Agents with Proactive Context Folding
132. ICLR 2026AgentGym-RL: An Open-Source Framework to Train LLM Agents for Long-Horizon Decision Making via Multi-Turn RL
133. ICLR 2026Agentic Collaboration as an Information Bottleneck Problem
134. ICLR 2026Agentic Context Engineering: Learning Comprehensive Contexts for Self-Improving Language Models
135. ICLR 2026Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models
136. ICLR 2026Agentic Reinforced Policy Optimization
137. ICLR 2026Agentic Reinforcement Learning with Implicit Step Rewards
138. ICLR 2026AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent
139. ICLR 2026AgentPO: Enhancing Multi-Agent Collaboration via Reinforcement Learning
140. ICLR 2026AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?
141. ICLR 2026AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents
142. ICLR 2026AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent Framework
143. ICLR 2026Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
144. ICLR 2026Alignment-Enhanced Integration of Connectivity and Spectral Sparse in Dynamic Sparse Training of LLM
145. ICLR 2026AlphaAgentEvo: Evolution-Oriented Alpha Mining via Self-Evolving Agentic Reinforcement Learning
146. ICLR 2026AlphaBench: Benchmarking Large Language Models in Formulaic Alpha Factor Mining
147. ICLR 2026AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations
148. ICLR 2026An Agentic Framework with LLMs for Solving Complex Vehicle Routing Problems
149. ICLR 2026Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven Analysis
150. ICLR 2026Analyzing and Evaluating Unbiased Language Model Watermark

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。