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 1,317 篇，第 25 / 27 页
- NeurIPS 2024Recursive Introspection: Teaching Language Model Agents How to Self-Improve
- NeurIPS 2024RedCode: Multi-dimensional Safety Benchmark for Code Agents
- NeurIPS 2024RedCode: Risky Code Execution and Generation Benchmark for Code Agents
- NeurIPS 2024Reflective Multi-Agent Collaboration based on Large Language Models
- NeurIPS 2024Reinforcing LLM Agents via Policy Optimization with Action Decomposition
- NeurIPS 2024RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models
- NeurIPS 2024RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space
- NeurIPS 2024Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy
- NeurIPS 2024RL-GPT: Integrating Reinforcement Learning and Code-as-policy
- NeurIPS 2024RoleAgent: Building, Interacting, and Benchmarking High-quality Role-Playing Agents from Scripts
- NeurIPS 2024Scalable Constrained Policy Optimization for Safe Multi-agent Reinforcement Learning
- NeurIPS 2024Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
- NeurIPS 2024Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments
- NeurIPS 2024SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction
- NeurIPS 2024SocraticLM: Exploring Socratic Personalized Teaching with Large Language Models
- NeurIPS 2024Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
- NeurIPS 2024Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning
- NeurIPS 2024StreamBench: Towards Benchmarking Continuous Improvement of Language Agents
- NeurIPS 2024SustainDC: Benchmarking for Sustainable Data Center Control
- NeurIPS 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
- NeurIPS 2024SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
- NeurIPS 2024Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale
- NeurIPS 2024T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition
- NeurIPS 2024TaskBench: Benchmarking Large Language Models for Task Automation
- NeurIPS 2024Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games
- NeurIPS 2024The Dormant Neuron Phenomenon in Multi-Agent Reinforcement Learning Value Factorization
- NeurIPS 2024Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
- NeurIPS 2024Understanding Model Selection for Learning in Strategic Environments
- NeurIPS 2024UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction
- NeurIPS 2024Using Unity to Help Solve Reinforcement Learning
- NeurIPS 2024Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training
- NeurIPS 2024VideoGUI: A Benchmark for GUI Automation from Instructional Videos
- NeurIPS 2024VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought
- NeurIPS 2024Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
- NeurIPS 2024WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control
- NeurIPS 2024Who’s Gaming the System? A Causally-Motivated Approach for Detecting Strategic Adaptation
- NeurIPS 2024WhodunitBench: Evaluating Large Multimodal Agents via Murder Mystery Games
- NeurIPS 2024WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks
- NeurIPS 2024WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment
- NeurIPS 2024YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals
- NeurIPS 2024ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination
- NeurIPS 2023AdaPlanner: Adaptive Planning from Feedback with Language Models
- NeurIPS 2023AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation
- NeurIPS 2023Alexa Arena: A User-Centric Interactive Platform for Embodied AI
- NeurIPS 2023AllSim: Simulating and Benchmarking Resource Allocation Policies in Multi-User Systems
- NeurIPS 2023AndroidInTheWild: A Large-Scale Dataset For Android Device Control
- NeurIPS 2023Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement Learning
- NeurIPS 2023Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings
- NeurIPS 2023AVIS: Autonomous Visual Information Seeking with Large Language Model Agent
- NeurIPS 2023BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks
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。