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 39 / 40 页
- NeurIPS 2026The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents
- NeurIPS 2026Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action
- NeurIPS 2026Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators
- NeurIPS 2026Time to Pay Attention! Understanding High Complexity Corpus Reasoning Tasks
- NeurIPS 2026TimeWarp: Evaluating Web Agents by Revisiting the Past
- NeurIPS 2026To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
- NeurIPS 2026TokenRouter: Efficient Serving System for Token-Level LLM Routing
- NeurIPS 2026ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
- NeurIPS 2026Tools as Continuous Flow for Evolving Agentic Reasoning
- NeurIPS 2026ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning
- NeurIPS 2026TopoScope: A Graph-Scoped LLM Agent for Printed Circuit Board Schematic Design
- NeurIPS 2026Toward Interactive Understanding of Code APIs
- NeurIPS 2026Toward Online Robust Zero-Sum Markov Games with Function Approximation
- NeurIPS 2026Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows
- NeurIPS 2026Towards Effective and Transferable Physical Camouflage against Multi-View BEV-based 3D Perception in Autonomous Driving
- NeurIPS 2026Towards High Semantic Fidelity: Hyperdimensional Symbolic Messages in Multi-Agent Communication
- NeurIPS 2026Towards Realistic Conversational Multimodal Instruction Following
- NeurIPS 2026Towards Reliable LLM Evaluation: Correcting the Winner’s Curse in Adaptive Benchmarking
- NeurIPS 2026Towards Unified Memory Adaptation for LLM Agents: Textual, Latent, and Parametric Pathways
- NeurIPS 2026TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development
- NeurIPS 2026Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations
- NeurIPS 2026Training Agent to Scale Inference-Time Reasoning
- NeurIPS 2026Training Generalizable Collaborative Agents via Strategic Risk Aversion
- NeurIPS 2026Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
- NeurIPS 2026Training on Documents About Monitoring Leads to CoT Obfuscation
- NeurIPS 2026TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents
- NeurIPS 2026Treat Domain-Specific Languages as Design Variables in LLM Agents
- NeurIPS 2026Tree Training: Efficient LLM Training on Tree-Structured Trajectories
- NeurIPS 2026TrialAgentBench: Evaluating AI Agents for Clinical-Trial Analysis and Long-Horizon Drug-Development Decisions
- NeurIPS 2026TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks
- NeurIPS 2026Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning
- NeurIPS 2026Trust, but Don’t Verify: Epistemic Blind Spots in LLM Source Evaluation
- NeurIPS 2026TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning
- NeurIPS 2026TwinFlux: One-Step Discrete-Continuous Flow for End-to-End Autonomous Driving
- NeurIPS 2026TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
- NeurIPS 2026Two is better than one: designing heterogeneous scales in binary rating systems
- NeurIPS 2026UMAS: System-Level Uncertainty Quantification for Multi-Agent LLM Systems
- NeurIPS 2026UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image
- NeurIPS 2026UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
- NeurIPS 2026Unified Resource-Grounded Coordination Protocol for Orchestrator-Free Heterogeneous Multi-Agent Systems
- NeurIPS 2026Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis
- NeurIPS 2026Untrusted Content Masking for Web Agents with Security Guarantees
- NeurIPS 2026Useful Memories Become Faulty When Continuously Updated by LLMs
- NeurIPS 2026Veri-Sure: Multi-Agent RTL Code Generation with Temporal Tracing, Slicing and Formal Verification
- NeurIPS 2026VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
- NeurIPS 2026VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora
- NeurIPS 2026VeruSAGE-Bench: A Benchmark Suite for Rust System Verification
- NeurIPS 2026VESTA: Visual Exploration with Statistical Tool Agents
- NeurIPS 2026VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation
- NeurIPS 2026VideoSleuth: A Narrative-Centric Agentic System with Video-Audio Native MLLM for Long-Form Video Understanding
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。