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 5 / 40 页
- ICLR 2026Correlated Policy Optimization in Multi-Agent Subteams
- ICLR 2026CP-Agent: Context‑Aware Multimodal Reasoning for Cellular Morphological Profiling under Chemical Perturbations
- ICLR 2026Credit-Budgeted ICPC-Style Coding: When LLM Agents Must Pay for Every Decision
- ICLR 2026CubeBench: Diagnosing Interactive, Long-Horizon Physical Intelligence under Partial Observations
- ICLR 2026Cyber-Zero: Training Cybersecurity Agents without Runtime
- ICLR 2026CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale
- ICLR 2026DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle
- ICLR 2026DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTS
- ICLR 2026DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science
- ICLR 2026Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
- ICLR 2026DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training
- ICLR 2026DAVE: A VLM Vision Encoder for Document Understanding and Web Agents
- ICLR 2026DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learning
- ICLR 2026DeepEyesV2: Toward Agentic Multimodal Model
- ICLR 2026DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
- ICLR 2026DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
- ICLR 2026Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents
- ICLR 2026Demystifying Deep Search: A Holistic Evaluation with Hint-free Multi-Hop Questions and Factorised Metrics
- ICLR 2026Denoising Neural Reranker for Recommender Systems
- ICLR 2026Detection of unknown unknowns in autonomous systems
- ICLR 2026DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle
- ICLR 2026Discovering Hierarchical Software Engineering Agents via Bandit Optimization
- ICLR 2026Discovering Novel LLM Experts via Task-Capability Coevolution
- ICLR 2026DiSRouter: Distributed Self-Routing for LLM Selections
- ICLR 2026Distributionally Robust Cooperative Multi-agent Reinforcement Learning with Value Factorization
- ICLR 2026Divide, Harmonize, Then Conquer It: Shooting Multi-Commodity Flow Problems with Multimodal Language Models
- ICLR 2026Do Large Language Models Know What They Are Capable Of?
- ICLR 2026Do LLM Agents Know How to Ground, Recover, and Assess? Evaluating Epistemic Competence in Information-Seeking Agents
- ICLR 2026Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning
- ICLR 2026Don't Just Fine-tune the Agent, Tune the Environment
- ICLR 2026Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect Personas
- ICLR 2026DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems
- ICLR 2026DRBench: A Realistic Benchmark for Enterprise Deep Research
- ICLR 2026DreamPhase: Offline Imagination and Uncertainty-Guided Planning for Large-Language-Model Agents
- ICLR 2026Drugging the Undruggable: Benchmarking and Modeling Fragment-Based Screening
- ICLR 2026Dual-Scale World Models for LLM Agents towards Hard-Exploration Problems
- ICLR 2026DualMap: Enabling Both Cache Affinity and Load Balancing for Distributed LLM Serving
- ICLR 2026Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
- ICLR 2026Dynamic Speculative Agent Planning
- ICLR 2026Earth-Agent: Unlocking the Full Landscape of Earth Observation with Agents
- ICLR 2026Efficient Agent Training for Computer Use
- ICLR 2026Eigen-1: Scientific Reasoning through Adaptive Multi-Agent Refinement and Monitor-based RAG
- ICLR 2026Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization
- ICLR 2026Emergent Coordination in Multi-Agent Language Models
- ICLR 2026Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking
- ICLR 2026Empowering LLM Tool Invocation with Tool-call Reward Model
- ICLR 2026Empowering Multi-Robot Cooperation via Sequential World Models
- ICLR 2026Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World
- ICLR 2026Enhancing Agentic Search via Data Synthesis on Hierarchical Constraint Satisfaction
- ICLR 2026Enhancing Complex Symbolic Logical Reasoning of Large Language Models via Sparse 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。