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 21 / 66 页
- ICML 2026Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
- ICML 2026Navigating the Energy Landscape of Collaboration: Multi-Agent Communication Graph Generation via Score-Based Diffusion
- ICML 2026NEMO: Execution-Aware Optimization Modeling via Autonomous Coding Agents
- ICML 2026Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense
- ICML 2026NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents
- ICML 2026NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search
- ICML 2026Not All Prefills Are Equal: PPD Disaggregation for Multi-turn LLM Serving
- ICML 2026Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics
- ICML 2026Off-Policy Evaluation with Strategic Agents via Local Disclosure
- ICML 2026Offline Multi-agent Continual Cooperation via Skill Partition and Reuse
- ICML 2026Offline Multi-Agent Reinforcement Learning via Sequential Score Decomposition
- ICML 2026OLion: Approaching the Hadamard Ideal by Intersecting Spectral and L inf Implicit Biases
- ICML 2026OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration
- ICML 2026On Effectiveness and Efficiency of Agentic Tool-calling and RL Training
- ICML 2026On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement
- ICML 2026On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents
- ICML 2026On Path to Multimodal Historical Reasoning: HistBench and HistAgent
- ICML 2026On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length
- ICML 2026One Tool Is Enough: Reinforcement Learning of LLM Agents for Repository-Level Code Navigation
- ICML 2026One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining
- ICML 2026Online Linear Programming for Multi-Objective Routing in LLM Serving
- ICML 2026OpenDeception: Learning Deception and Trust in Human–AI Interaction via Multi-Agent Simulation
- ICML 2026OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft
- ICML 2026OpenSage: Self-programming Agent Generation Engine
- ICML 2026Ophiuchus: Incentivizing Tool-augmented ''Think with Images'' for Joint Medical Segmentation, Understanding and Reasoning
- ICML 2026Opt-Miner: Empowering Information-Seeking Agent with Tree-Guided Data Synthesis for Optimization Modeling
- ICML 2026Optimal and Scalable MAPF via Multi-Marginal Optimal Transport and Schrödinger Bridges
- ICML 2026Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers
- ICML 2026Optimal Rates for Feasible Payoff Set Estimation in Games
- ICML 2026Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward
- ICML 2026OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing
- ICML 2026OServe: Accelerating LLM Serving via Spatial-Temporal Workload Orchestration
- ICML 2026OSM+: Billion-Level Open Street Map Dataset for City-wide Experiments
- ICML 2026OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
- ICML 2026Outrunning LLM Cutoffs: A Live Kernel Crash Resolution Benchmark for All
- ICML 2026PaperBanana: Automating Academic Illustration for AI Scientists
- ICML 2026ParamMem: Augmenting Language Agents with Parametric Reflective Memory
- ICML 2026ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution
- ICML 2026PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs
- ICML 2026PDAgent: An LLM-Driven Autonomous Agent Framework Towards *In Silico* Protein Design via Directed Mutation
- ICML 2026Persistent Semantic Entities in Tool-Augmented LLM Systems
- ICML 2026Persona-Pruner: Sculpting Lightweight Models for Role-Playing
- ICML 2026Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History
- ICML 2026Pessimistic Verification for Open-Ended Math Questions
- ICML 2026PGS: Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback
- ICML 2026Phase-Aware Mixture of Experts for Agentic Reinforcement Learning
- ICML 2026PinTok: Tokenizers Deserve Dedicated Pinned CPU-Compute and Memory
- ICML 2026Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control
- ICML 2026PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
- ICML 2026POLCA: Stochastic Generative Optimization with LLM
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。