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 1,317 篇，第 11 / 27 页
- NeurIPS 2026PurpleAudit: A Co-Evolutionary Auditing Framework for Task Hijacking in Multi-Agent Systems
- NeurIPS 2026Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing
- NeurIPS 2026QUEST: Q-Learning for Uncertainty-Guided Efficient Search Teams
- NeurIPS 2026RA$^2$: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning
- NeurIPS 2026RADAR: Routing Agents via Difficulty-Aware Recovery
- NeurIPS 2026RAG in a Trenchcoat: When Minimal Memory Is Enough for Agentic Systems, and When It Isn’t
- NeurIPS 2026RAOP: Step-Level Resource Orchestration for LLM Agents across Edge and Cloud
- NeurIPS 2026Rare Disease Diagnosis Agent with Decoupled Workflows and Knowledge-Driven Self-Evaluation
- NeurIPS 2026ReCoVer: Resilient LLM Pre-Training System via Fault-Tolerant Collective and Versatile Workload
- NeurIPS 2026Recovering the Apresjan Hierarchy Using Linkage-Based Clustering
- NeurIPS 2026Recursive Multi-Agent Systems
- NeurIPS 2026ReGen: Agentic Video World Modeling with Synergized Reasoning and Generation
- NeurIPS 2026REINS: A Self-Evolving Agent Harness for Real-Time Trajectory Planning
- NeurIPS 2026RelAgent: LLM Agents as Data Scientists for Relational Learning
- NeurIPS 2026Relevance Is Not Necessity: Selecting the Necessary API Set for Tool-Using LLMs
- NeurIPS 2026Replicas-as-Variables: A Planner for Throughput-Optimal Routing in LLM Deployment
- NeurIPS 2026RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
- NeurIPS 2026RepoZero: Can LLMs Generate a Code Repository from Scratch?
- NeurIPS 2026Resilience Matters for Embodied Agents System: New Metrics, Systematic Evaluation, and Optimization
- NeurIPS 2026Rethinking Bayesian Optimization for Co-Optimizing LLM Training Configurations
- NeurIPS 2026Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
- NeurIPS 2026Rethinking in Spikes: Mitigating Hallucinations in MDLMs with Step-Aware Decoding
- NeurIPS 2026Rethinking Latency Denial-of-Service: Attack the LLM Serving Framework, Not the Model
- NeurIPS 2026Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning
- NeurIPS 2026REVERSE: Reinforcing Evidence Verification and Search for Agentic Image Geolocation
- NeurIPS 2026Reward Modeling for Multi-Agent Orchestration
- NeurIPS 2026RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with LLMs
- NeurIPS 2026RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents
- NeurIPS 2026RIGOR: Risk-Gated Topology Adaptation for Robust LLM Multi-Agent Reasoning
- NeurIPS 2026Risk-Calibrated Context Selection for Healthcare Multi-Agent Handoff
- NeurIPS 2026RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agents
- NeurIPS 2026RL-Guided Temporal Localization for Dual-Channel Retrieval in Long-Horizon Agent Memory
- NeurIPS 2026RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades
- NeurIPS 2026RoboWits: Unexpected Challenges for Robotic Creative Problem Solving
- NeurIPS 2026Routeability Before Routing: Routeability Audit Protocol (RAP) and RouteabilityBench for Audited LLM Model Selection
- NeurIPS 2026RTEB: An Overfitting-Resistant Benchmark for Embedding Model Evaluation
- NeurIPS 2026RuleSmith: Multi-Agent LLMs for Automated Game Balancing
- NeurIPS 2026Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic
- NeurIPS 2026RVR: Retrieve-Verify-Retrieve for Comprehensive Question Answering
- NeurIPS 2026S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields
- NeurIPS 2026SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?
- NeurIPS 2026SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering
- NeurIPS 2026Safe Actions Can Form Unsafe Traces: Benchmarking and Shielding Compositional Emergent Risk in AI Agents
- NeurIPS 2026Safe-Fair MACPO: Burden-Fair Constrained Policy Optimization for Safe Multi-Agent Reinforcement Learning
- NeurIPS 2026Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents
- NeurIPS 2026SageSched: Efficient LLM Scheduling Confronting Demand Uncertainty and Hybridity
- NeurIPS 2026Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents
- NeurIPS 2026Sandboxed Coding Agents are Competitive Omni-modal Task Solvers
- NeurIPS 2026Scalable Minimal-Change Learning for Controllable Image Editing
- NeurIPS 2026Scalable Multi-Agent Contrastive Reinforcement Learning
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。