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 729 篇，第 4 / 15 页
- NeurIPS 2026Control Charts for Multi-Agent Systems
- NeurIPS 2026Controllable Road Marking Generation
- NeurIPS 2026Convergence Guarantees for Federated SARSA with Local Training and Heterogeneous Agents
- NeurIPS 2026Cooperative Multi-Agent Reinforcement Learning via Epigraph-Form Guided Exploration
- NeurIPS 2026Coordinating Hundreds of RL Agents through Scalable Inference-Time Search
- NeurIPS 2026Coordination Connectivity: Shared Initialization Shapes the Joint-Policy Landscape in MARL
- NeurIPS 2026COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams
- NeurIPS 2026Counterfactual Distillation: Internalizing Reflective Experience into LLM Agent
- NeurIPS 2026CounterStrike-1K: A Multi-Perspective Dataset of Professional Gameplay for World Modeling
- NeurIPS 2026CoupledFlow: One-Step Neural Operators for Coupled Multi-Physics PDEs
- NeurIPS 2026Coupling-Aware Reinforcement Learning for Co-Evolving Graph Games
- NeurIPS 2026CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter
- NeurIPS 2026CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
- NeurIPS 2026CREF: Forecasting Benchmarks for the Age of Agents
- NeurIPS 2026Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse
- NeurIPS 2026Cross-User Poisoning: User-Task Boundary Failures in Multi-User Collaborative Language Agents
- NeurIPS 2026CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness
- NeurIPS 2026CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging
- NeurIPS 2026CURE: Coupled User-Grouped Reinforcement Learning for Cross-Domain Recommendation with Non-Overlapping Users
- NeurIPS 2026CyberDualEval: Measuring Dual-Use Cyber Risks in Frontier Language Models
- NeurIPS 2026CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios
- NeurIPS 2026DAGent: Evaluate-then-Grow Planning for Deep Research Agents
- NeurIPS 2026DDACOM: Dual-Decoupled Adaptive Communication for Multi-Agent Reinforcement Learning under Dynamic Networks
- NeurIPS 2026DDBench: A Benchmark for Agentic Debugging on Distributed Systems
- NeurIPS 2026DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems
- NeurIPS 2026Decentralized Multi-Goal Multi-Agent Pathfinding with Spatial Prior and Neighbor Intent Prediction
- NeurIPS 2026Decentralized Q-Learning in Markov Potential Games
- NeurIPS 2026Deep Reasoning in General Purpose Agents via Structured Meta-Cognition
- NeurIPS 2026Deep Research as Rubric
- NeurIPS 2026DeepArrhythmia: Segment-Contextualized ECG Arrhythmia Classification via Selective Evidence Acquisition
- NeurIPS 2026Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents
- NeurIPS 2026DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents
- NeurIPS 2026DICE: Decoupling Capability from Intervention Necessity in LLM Tutoring
- NeurIPS 2026Differentiable Belief-based Opponent Shaping
- NeurIPS 2026DIS-Bench: Evaluating LLMs on System Testing via Directed Input Synthesis
- NeurIPS 2026Discovering Phase Space Structure in Learned Hamiltonian Systems
- NeurIPS 2026DiscoverPhysics: Benchmarking LLMs for out-of-the-box scientific thinking
- NeurIPS 2026DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems?
- NeurIPS 2026Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests
- NeurIPS 2026Do Joint Audio-Video Generation Models Understand Physics?
- NeurIPS 2026DocAtlas: Long-Document Understanding as Mutable-State Interaction
- NeurIPS 2026Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble Selection
- NeurIPS 2026Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents
- NeurIPS 2026Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
- NeurIPS 2026DualWorldBench: Can Agents Plan Deliveries across Symbolic and Grounded Worlds?
- NeurIPS 2026ECG Dataset with Multi-Expert Annotations and Delineations
- NeurIPS 2026Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
- NeurIPS 2026Effective Knowledge Conflict Detection via Joint Agentic Optimization
- NeurIPS 2026Efficient evaluation and error pattern discovery for blackbox AI systems
- NeurIPS 2026Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management
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。