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 729 篇，第 9 / 15 页
- NeurIPS 2026Mind the Gap: Information Disadvantage as a Learning Signal in Cooperative MARL
- NeurIPS 2026MindGames:A Multi-Agent Benchmark and Trajectory Dataset for Evaluating Social and Strategic Reasoning in LLMs
- NeurIPS 2026MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents
- NeurIPS 2026MiniPIC: Flexible Position-Independent Caching in <100LOC
- NeurIPS 2026Mirror, Mirror on the Wall: Can VLM Agents Tell Who They Are at All?
- NeurIPS 2026MLLMs Fail to Refuse when Using Tools Agentically
- NeurIPS 2026MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
- NeurIPS 2026MMGraph-Agent: Agentic Multimodal RAG via Cache-Inspired Multimodal Knowledge HyperGraphs
- NeurIPS 2026MMSkills: Towards Multimodal Skills for General Visual Agents
- NeurIPS 2026Mode-Controlled Policy Optimization: A Geometry-Aware Recipe for LLM Post-Training
- NeurIPS 2026Model Incrimination: Investigating Whether Concerning Behavior Reflects Misalignment
- NeurIPS 2026Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use
- NeurIPS 2026Modelling Opinion Dynamics at Scale with Deep MARL
- NeurIPS 2026Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation
- NeurIPS 2026MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens
- NeurIPS 2026More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models
- NeurIPS 2026More Value per Key: Asymmetric Sparse Attention for Faster LLM Decoding
- NeurIPS 2026MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
- NeurIPS 2026MOSAIC: Scaling Long-Horizon Language Agents via Multi-Scale Adaptive Inference Control
- NeurIPS 2026Motion Forcing: Decoupling Ego and Object Motion via Sparse Inputs for Structured Video Generation
- NeurIPS 2026MPCI-Bench: A Benchmark for Multimodal Pairwise Contextual Integrity Privacy Evaluation of Language Model Agents
- NeurIPS 2026Multi-agent Collaboration with State Management
- NeurIPS 2026Multi-Agent Coordination via Support-Preserving Distillation
- NeurIPS 2026Multi-bit LLM Watermarking with Certified Semantic Distortion
- NeurIPS 2026MultiSTEVE-1s: A Model Zoo and Interpretability Suite for Instruction-Following Vision Agents
- NeurIPS 2026NARRA-Gym for Evaluating Interactive Narrative Agents
- NeurIPS 2026Narrowing the Collaboration Gap, Probably
- NeurIPS 2026Nautilus: From One Prompt to Plug-and-Play Robot Learning
- NeurIPS 2026Need-Aware Multi-Objective Reinforcement Learning for Emotionally Intelligent LLM Agents
- NeurIPS 2026Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
- NeurIPS 2026NEST: Nascent Encoded Steganographic Thoughts
- NeurIPS 2026NestRL: A Nested Training Regime for Mutual Adaptation in Human–AI Teaming
- NeurIPS 2026NeSyKC: Neurosymbolic Knowledge Compilation For Lifelong Learning Embodied Agents
- NeurIPS 2026NesyProAct: Proactive Neural-Symbolic Control for Web Agents
- NeurIPS 2026NINJA: A Navigator–Inspector Joint Architecture for Context-Efficient Issue Localization
- NeurIPS 2026NitroBox: Lightning-Fast Sandbox for Large-Scale RL Training
- NeurIPS 2026No Model Required: Text Entropy Rate Filtering Prevents Iterative Fine-Tuning Collapse
- NeurIPS 2026Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems
- NeurIPS 2026Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness
- NeurIPS 2026ODDR: One-Step Deshadow Diffusion via Reward Guidance
- NeurIPS 2026OfficeInstruct: A Dataset for Tool-Augmented Office Agents on Long-Trajectory Generative Tasks
- NeurIPS 2026Offline Preference-Based Trajectory Evaluation
- NeurIPS 2026On Data Engineering for Scaling LLM Terminal Capabilities
- NeurIPS 2026On the Impact of Side-Information in Bandit Learning: More is Not Always Merrier
- NeurIPS 2026On the Nonlinearity of Learning Rate Scaling for LLM Training
- NeurIPS 2026One Adapter For All: Towards Generalizable Many-To-One Domain Adaptation In Heterogeneous Collaborative Perception
- NeurIPS 2026One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning
- NeurIPS 2026Online Fair Division Meets Reordering Buffers
- NeurIPS 2026Online Learning in Stabilized Linear Dynamical Games with Adversarial Disturbances
- NeurIPS 2026OntoPlan: An Ontology-Grounded Scene Representation and Agentic Framework for Scalable Robot Task Planning
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。