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 12 / 27 页
- NeurIPS 2026SceneFactory: GPU-Accelerated Multi-Agent Driving Simulation with Physics-Based Vehicle Dynamics
- NeurIPS 2026SchemeArena: Factorized Stress Testing of Scheming in LLM Agents
- NeurIPS 2026SCHOLARPEER: A Multi-Agent Framework for Automated Peer Review
- NeurIPS 2026SciResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery
- NeurIPS 2026ScrapeBench: Evaluating Legal Compliance of AI Agents in Website Scraping
- NeurIPS 2026scShapeBench: Discovering geometry from high dimensional scRNAseq data
- NeurIPS 2026SeaPilot: Mobile Agent with Self-refining Environment Alignment
- NeurIPS 2026SecureClaw: Clawing Back Control of LLM Agents
- NeurIPS 2026Securing AI Agents with Information-Flow Control
- NeurIPS 2026Seeing Beyond the Next Step: World-Model-Guided Human-Like Navigation in Multi-Agent Scenes
- NeurIPS 2026SEEK-VAU: Towards Evidence-Faithful Video Anomaly Understanding via Agentic Search
- NeurIPS 2026Selective Answering for Medical VQA via Parallel Independent Claim Verification
- NeurIPS 2026Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL
- NeurIPS 2026Self-Compacting Language Model Agents
- NeurIPS 2026Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback
- NeurIPS 2026Self-Evolving Agents Should Build Internal and External Models of the World
- NeurIPS 2026Self-Programmed Execution for Language-Model Agents
- NeurIPS 2026Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration
- NeurIPS 2026Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation
- NeurIPS 2026Sequential Behavioral Watermarking for LLM Agents
- NeurIPS 2026Sharpness, Stability, and Step-Size Scaling in Deep Polynomial Networks
- NeurIPS 2026Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace
- NeurIPS 2026SIGA: Scientific Simulation Coding Agent Adapter- A Geophysics Case Study
- NeurIPS 2026SiliconBench: Speed, Memory, and Fidelity for LLM Inference on Apple Silicon
- NeurIPS 2026Simple Baselines are Competitive with Code Evolution
- NeurIPS 2026Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
- NeurIPS 2026Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
- NeurIPS 2026SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
- NeurIPS 2026SkillMaster: Toward Autonomous Skill Mastery in LLM Agents
- NeurIPS 2026SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- NeurIPS 2026SkillOrchestra: Learning to Route Agents via Skill Transfer
- NeurIPS 2026SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- NeurIPS 2026SKIM: Pruning Large Language Model Agents via Selective Knowledge Informed Masking
- NeurIPS 2026Slide P2V-Bench: A Cross-Domain Benchmark for Slide-Centric Scientific Paper-to-Presentation Video Generation
- NeurIPS 2026SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
- NeurIPS 2026SMART: Scalable Multi-Agent Role-conditioned Teaming via LLM-free Tree Search
- NeurIPS 2026Social Interaction Breaks Replicate Independence in Controlled-Clone LLM Agents
- NeurIPS 2026SoDeArena: A Socially-Situated Reasoning Benchmark for Large Language Models
- NeurIPS 2026SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits
- NeurIPS 2026SOLAR: AI-Powered Speed-of-Light Performance Analysis
- NeurIPS 2026Solaris: Building a Multiplayer Video World Model in Minecraft
- NeurIPS 2026Solving Every Step Is Not Enough: Milestone Oracles Reveal a Composition Gap in LLM Math Reasoning
- NeurIPS 2026Soteria: Formally Verified Planning with Runtime Enforcement for Safe LLM Agents
- NeurIPS 2026SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference
- NeurIPS 2026SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
- NeurIPS 2026SpecForge: Agent-Oriented Code Documentation Optimization via Multi-Frontier Tree Search
- NeurIPS 2026Specialists Hold, Generalists Discount: Asymmetric Equilibrium in LLM Routing Auctions
- NeurIPS 2026Spend Only What You Need: Defect-Aware Residual Coverage for Efficient Multi-Agent Reasoning
- NeurIPS 2026SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving
- NeurIPS 2026SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows
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。