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 4 / 66 页
- ICLR 2026AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs
- ICLR 2026AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite
- ICLR 2026ATLAS: Constraints-Aware Multi-Agent Collaboration for Real-World Travel Planning
- ICLR 2026Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test
- ICLR 2026AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations
- ICLR 2026AutoLibra: Agent Metric Induction from Open-Ended Human Feedback
- ICLR 2026Automated Stateful Specialization for Adaptive Agent Systems
- ICLR 2026AutoSP: Unlocking Long-Context LLM Training Via Compiler-Based Sequence Parallelism
- ICLR 2026Bayesian Robust Cooperative Multi-Agent Reinforcement Learning Against Unknown Adversaries
- ICLR 2026BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning
- ICLR 2026BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design
- ICLR 2026Benchmarking LLM Tool-Use in the Wild
- ICLR 2026Benchmarking Multi-Agent Reinforcement Learning in Power Grid Operations
- ICLR 2026Benefits and Limitations of Communication in Multi-Agent Reasoning
- ICLR 2026Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE
- ICLR 2026Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts
- ICLR 2026Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining
- ICLR 2026BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
- ICLR 2026BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic Interactions
- ICLR 2026Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents
- ICLR 2026Breaking and Fixing Defenses Against Control Flow Hijacking in Multi-Agent Systems
- ICLR 2026BRIDGE: Bi-level Reinforcement Learning for Dynamic Group Structure in Coalition Formation Games
- ICLR 2026Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
- ICLR 2026Cache-to-Cache: Direct Semantic Communication Between Large Language Models
- ICLR 2026Can Language Models Discover Scaling Laws?
- ICLR 2026Cancer-Myth: Evaluating Large Language Models on Patient Questions with False Presuppositions
- ICLR 2026CARD: Towards Conditional Design of Multi-agent Topological Structures
- ICLR 2026CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework
- ICLR 2026Catalog-Native LLM: Speaking Item-ID dialect with Less Entanglement for Recommendation
- ICLR 2026CellAgent: LLM-Driven Multi-Agent Framework for Natural Language-Based Single-Cell Analysis
- ICLR 2026CellDuality: Unlocking Biological Reasoning in LLMs with Self-Supervised RLVR
- ICLR 2026ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
- ICLR 2026ChinaTravel: An Open-Ended Travel Planning Benchmark with Compositional Constraint Validation for Language Agents
- ICLR 2026CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context Engineering
- ICLR 2026CoAct-1: Computer-using Multi-agent System with Coding Actions
- ICLR 2026CoDA: Agentic Systems for Collaborative Data Visualization
- ICLR 2026Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration
- ICLR 2026CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control
- ICLR 2026CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
- ICLR 2026CoMind: Towards Community-Driven Agents for Machine Learning Engineering
- ICLR 2026Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing
- ICLR 2026Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks
- ICLR 2026Computer Agent Arena: Toward Human-Centric Evaluation and Analysis of Computer-Use Agents
- ICLR 2026ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
- ICLR 2026CoNavBench: Collaborative Long-Horizon Vision-Language Navigation Benchmark
- ICLR 2026Context Learning for Multi-Agent Discussion
- ICLR 2026ContextNav: Towards Agentic Multimodal In-Context Learning
- ICLR 2026Continual Low-Rank Adapters for LLM-based Generative Recommender Systems
- ICLR 2026Continuous-Time Value Iteration for Multi-Agent Reinforcement Learning
- ICLR 2026Control Tax: The Price of Keeping AI in Check
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。