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 1,983 篇，第 9 / 40 页
- ICLR 2026MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation
- ICLR 2026Monitoring Decomposition Attacks with Lightweight Sequential Monitors
- ICLR 2026Multi-Action Self-Improvement For Neural Combinatorial Optimization
- ICLR 2026Multi-agent Coordination via Flow Matching
- ICLR 2026Multi-Agent Debate with Memory Masking
- ICLR 2026Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies
- ICLR 2026Multi-Agent Guided Policy Optimization
- ICLR 2026Multi-LLM Adaptive Conformal Inference for Reliable LLM Response
- ICLR 2026Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflows
- ICLR 2026Multimodal Policy Internalization for Conversational Agents
- ICLR 2026Negotiated Reasoning: On Provably Addressing Relative Over-Generalization
- ICLR 2026NerVE: Nonlinear Eigenspectrum Dynamics in LLM Feed-Forward Networks
- ICLR 2026NetArena: Dynamically Generated LLM Benchmarks for Network Applications
- ICLR 2026NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents
- ICLR 2026Non-Collaborative User Simulators for Tool Agents
- ICLR 2026Not All Clients Are Equal: Collaborative Model Personalization on Heterogeneous Multi-Modal Clients
- ICLR 2026NRGPT: An Energy-based Alternative for GPT
- ICLR 2026OccDriver: Future Occupancy Guided Dual-branch Trajectory Planner in Autonomous Driving
- ICLR 2026OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!
- ICLR 2026Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception
- ICLR 2026OmniActor: A Generalist GUI and Embodied Agent for 2D&3D Worlds
- ICLR 2026One Skill, Many Websites: Learning Generalizable Skills Through Polymorphic Abstraction
- ICLR 2026OpenAgentSafety: A Comprehensive Framework For Evaluating Real-World AI Agent Safety
- ICLR 2026OpenApps: Simulating Environment Variations to Measure UI Agent Reliability
- ICLR 2026Opponent Shaping in LLM Agents
- ICLR 2026OPRIDE: Efficient Offline Preference-based Reinforcement Learning via In-Dataset Exploration
- ICLR 2026Optimal Robust Subsidy Policies for Irrational Agent in Principal-Agent MDPs
- ICLR 2026Optimizing Agent Planning for Security and Autonomy
- ICLR 2026Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games
- ICLR 2026OrchestrationBench: LLM-Driven Agentic Planning and Tool Use in Multi-Domain Scenarios
- ICLR 2026OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents
- ICLR 2026P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark
- ICLR 2026PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities
- ICLR 2026Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding
- ICLR 2026Paper Copilot: Tracking the Evolution of Peer Review in AI Conferences
- ICLR 2026Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
- ICLR 2026PerfGuard: A Performance-Aware Agent for Visual Content Generation
- ICLR 2026Personalized Collaborative Learning with Affinity-Based Variance Reduction
- ICLR 2026PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement
- ICLR 2026PixelCraft: A Multi-Agent system for High-Fidelity Visual Reasoning on Structured Images
- ICLR 2026PLAGUE: Plug-and-play Framework for Lifelong Adaptive Generation of Multi-turn Exploits
- ICLR 2026Potentially Optimal Joint Actions Recognition for Cooperative Multi-Agent Reinforcement Learning
- ICLR 2026Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations
- ICLR 2026Prima.cpp: Fast 30-70B LLM Inference on Heterogeneous and Low-Resource Home Clusters
- ICLR 2026PRISM: Festina Lente Proactivity—Risk-Sensitive, Uncertainty-Aware Deliberation for Proactive Agents
- ICLR 2026Process-Level Trajectory Evaluation for Environment Configuration in Software Engineering Agents
- ICLR 2026Programming with Pixels: Can Computer-Use Agents do Software Engineering?
- ICLR 2026ProofOptimizer: Training Language Models to Simplify Proofs without Human Demonstrations
- ICLR 2026PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach
- ICLR 2026ProRe: A Proactive Reward System for GUI Agents via Reasoner–Actor Collaboration
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。