AI 智能体论文趋势 2023–2026
工具调用、多步决策与自主 LLM/VLM 智能体系统
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 3,266 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 76 | 40 | 41 | 13 | 170 |
| 2024 | 150 | 73 | 88 | 18 | 329 |
| 2025 | 362 | 204 | 178 | 40 | 784 |
| 2026 | 729 | 500 | 640 | 114 | 1,983 |
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 55 / 66 页
- NeurIPS 2025Simulating Society Requires Simulating Thought
- NeurIPS 2025Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models
- NeurIPS 2025SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds
- NeurIPS 2025SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
- NeurIPS 2025SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific Sketches
- NeurIPS 2025Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation is Wasteful
- NeurIPS 2025SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
- NeurIPS 2025SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions
- NeurIPS 2025SpecEM: Training-Free LLM Ensembling via Iterative Drafting, Verification, and Online Feedback
- NeurIPS 2025SpecMAS: A Multi-Agent System for Self-Verifying System Generation via Formal Model Checking
- NeurIPS 2025SSRB: Direct Natural Language Querying to Massive Heterogeneous Semi-Structured Data
- NeurIPS 2025Stabilizing LTI Systems under Partial Observability: Sample Complexity and Fundamental Limits
- NeurIPS 2025Stackelberg Learning with Outcome-based Payment
- NeurIPS 2025STEER-ME: Assessing the Microeconomic Reasoning of Large Language Models
- NeurIPS 2025STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Clouds
- NeurIPS 2025Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs
- NeurIPS 2025SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications
- NeurIPS 2025SWE-bench Goes Live!
- NeurIPS 2025SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
- NeurIPS 2025SWE-smith: Scaling Data for Software Engineering Agents
- NeurIPS 2025SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset
- NeurIPS 2025SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assembly
- NeurIPS 2025Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning
- NeurIPS 2025Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration
- NeurIPS 2025T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning
- NeurIPS 2025TAI3: Testing Agent Integrity in Interpreting User Intent
- NeurIPS 2025Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
- NeurIPS 2025The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements
- NeurIPS 2025The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement
- NeurIPS 2025TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
- NeurIPS 2025Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
- NeurIPS 2025Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time Interaction
- NeurIPS 2025Thought Communication in Multiagent Collaboration
- NeurIPS 2025Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
- NeurIPS 2025Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking
- NeurIPS 2025TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop
- NeurIPS 2025ToolRL: Reward is All Tool Learning Needs
- NeurIPS 2025Towards Doctor-Like Reasoning: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients
- NeurIPS 2025Towards Principled Unsupervised Multi-Agent Reinforcement Learning
- NeurIPS 2025TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration
- NeurIPS 2025Transcending Cost-Quality Tradeoff in Agent Serving via Session-Awareness
- NeurIPS 2025Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning
- NeurIPS 2025TRAP: Targeted Redirecting of Agentic Preferences
- NeurIPS 2025Tri-MARF: A Tri-Modal Multi-Agent Responsive Framework for Comprehensive 3D Object Annotation
- NeurIPS 2025TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets
- NeurIPS 2025UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents
- NeurIPS 2025UniMotion: A Unified Motion Framework for Simulation, Prediction and Planning
- NeurIPS 2025URB - Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles
- NeurIPS 2025UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception
- NeurIPS 2025Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
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AI 智能体在 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": "ai-agents"}
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。