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 14 / 66 页
- ICML 2026Agentic Model Predictive Questioning Control in Visual Design
- ICML 2026Agentic Monte Carlo: Simulating Reinforcement Learning for Black-Box Agents
- ICML 2026Agentic Proposing: Enhancing Large language Model Reasoning via Compositional Skill Synthesis
- ICML 2026AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks
- ICML 2026AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition
- ICML 2026AgentSelect: Benchmark for Narrative Query-to-Agent Recommendation
- ICML 2026AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech
- ICML 2026AgentSuite: Toward More Reliable Agent Evaluation with a Component-Based Benchmark Auditing Pipeline
- ICML 2026AgentTailor: A Semantic-Aware LLM-Based Multi-Agent System with Actor-Critic Structure
- ICML 2026AgentVocab: Structure-Aware Vocabulary Adaptation for Efficient LLM Agents
- ICML 2026AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Web
- ICML 2026AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction
- ICML 2026Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM Agents
- ICML 2026AIR: Improving Agent Safety through Incident Response
- ICML 2026ALSO: Adversarial Online Strategy Optimization for Social Agents
- ICML 2026AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
- ICML 2026An Interactive Paradigm for Deep Research
- ICML 2026AnalogVerifier: A Neuro-Symbolic Framework for Analog Circuit Verification
- ICML 2026ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm
- ICML 2026Anytime Detection of Strategic Deviations in Multi-Agent Systems
- ICML 2026AOEB: Benchmarking Agent-Oriented Multimodal Embeddings
- ICML 2026AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
- ICML 2026AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use
- ICML 2026Architecture Matters for Multi-Agent Security
- ICML 2026Are Your Agents Upward Deceivers?
- ICML 2026ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
- ICML 2026ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning
- ICML 2026Ask Less, See More: Communication-Conditioned Token Pruning for Vehicle-to-Vehicle Cooperative Autonomous Driving with Multimodal Large Language Models
- ICML 2026AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters
- ICML 2026AtomWorld: A Benchmark for Evaluating Spatial Reasoning in Large Language Models on Material Structures
- ICML 2026Autobidding Auctions with LLM-Powered Creatives
- ICML 2026AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
- ICML 2026AutoMat: Physics-Guided Agentic Reasoning for Solving Ill-Posed Inverse Microscopy Problems
- ICML 2026Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning
- ICML 2026Automatic Construction of Clinical Scoring Systems with LLM Agents
- ICML 2026AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure Design
- ICML 2026AutoRAS: Learning Robust Agentic Systems with Primitive Representations
- ICML 2026AutoRPA: Efficient GUI Automation through LLM-Driven Code Synthesis from Interactions
- ICML 2026AutoSizer: Automatic Sizing of Analog and Mixed-Signal Circuits via Large Language Model (LLM) Agents
- ICML 2026AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning
- ICML 2026AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines
- ICML 2026B-Spar: Bayesian Sparse-Reward Modeling for RL-based Image Editing
- ICML 2026Backjump-on-Graph: Empowering Large Language Models with Reinforced Retrospective Exploration for Agentic Knowledge Graph Reasoning
- ICML 2026Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning
- ICML 2026Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks
- ICML 2026BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate
- ICML 2026Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks
- ICML 2026Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Hunting
- ICML 2026Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork
- ICML 2026Beyond Correctness: Distance-Based Social Dynamics of Multi-Agent Debate
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。