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 5 / 15 页
- NeurIPS 2026EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
- NeurIPS 2026EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents
- NeurIPS 2026Embedded-Arena: Building Hardware-in-the-Loop Coding Agents to Run AI on Microcontrollers
- NeurIPS 2026Empirical Bayes Rebiasing
- NeurIPS 2026EngramState: Loadable Tool Priors for Efficient Function Calling
- NeurIPS 2026Enhancing Agentic Code Localization with Traceability Recovered from Repository Evolution
- NeurIPS 2026Entropy Dynamics of Agent Reinforcement Learning
- NeurIPS 2026Epistemic Pairwise Maximin Share
- NeurIPS 2026Epistemic Social Learning: Latent Behavioral Structure under Endogenous Multi-Agent Interaction
- NeurIPS 2026Ergodic Trajectory Design by Learned Pushforward Maps: Provable Coverage via Conditional Flow Matching
- NeurIPS 2026EVA: Evidence-seeking Visual Agent for Hallucination-Resistant Multimodal Reasoning
- NeurIPS 2026Evaluating Physical Reasoning in LLM Agents Requires Construction Benchmarks
- NeurIPS 2026Evaluating Test-Time Scaling of General LLM Agents
- NeurIPS 2026Every Bit, Everywhere, All At Once: A Binomial Multibit LLM Watermark
- NeurIPS 2026EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales
- NeurIPS 2026EvoCodeBench: Evaluating Coding Agents in Multi-Turn Iterative Interactions
- NeurIPS 2026EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
- NeurIPS 2026EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution
- NeurIPS 2026EvoInspect: A Unified Self-Evolving Multi-Agent Framework for Industrial Hardware Inspection
- NeurIPS 2026Evolutionary System Prompt Learning for Reinforcement Learning in LLMs
- NeurIPS 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
- NeurIPS 2026EvoMM: Reinforced Self-Evolving Multimodal Agentic Memory
- NeurIPS 2026EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling
- NeurIPS 2026ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling
- NeurIPS 2026Exemplar2VQA: A Scalable Exemplar-Driven Visual Question Answering Generation Framework via Multi-Agent Coding
- NeurIPS 2026Expanding LLM Agent Boundaries with Strategy-Guided Exploration
- NeurIPS 2026Explanations over Graphs: An Agent Architecture for IT Enterprise Diagnostic Tasks
- NeurIPS 2026ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
- NeurIPS 2026Extrapolative Weight Averaging Reveals Correctness–Efficiency Frontiers in Code RL
- NeurIPS 2026Fair Division of Work in Collaborative Mean Estimation via Bargaining
- NeurIPS 2026FASD: Hardware Acceleration for Multi-AI-Agent Discussion
- NeurIPS 2026Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction
- NeurIPS 2026FedProG: Federated Graph Learning via Server-Side LLM Semantic Bridging and Uncertainty-Aware Distillation
- NeurIPS 2026FEP-Agent: Grounding LLM Agent Self-Evolution in Active Inference with Semantic Memory
- NeurIPS 2026Fine-Grained Benchmark Generation for Comprehensive Evaluation of Foundation Models
- NeurIPS 2026Fingerprinting Inference Systems of Large Language Models
- NeurIPS 2026Finite-Sample Convergence in Networked Average Reward MARL: Decentralization Pitfalls and Entropy Remedies
- NeurIPS 2026FinReasoning: A Hierarchical Benchmark for Reliable Financial Research Reporting
- NeurIPS 2026Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
- NeurIPS 2026Fix the Structural Bottleneck: Context Compression via Explicit Information Transmission
- NeurIPS 2026FLARE: Verifying MILP Reformulations with LLM-Based Formal Proof Synthesis
- NeurIPS 2026FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration
- NeurIPS 2026Flow Matching for Offline Reinforcement Learning with Discrete Actions
- NeurIPS 2026FlowLeak: Coverage-Guided Extraction of Dynamic Workflows in LLM-Based Multi-Agent Systems
- NeurIPS 2026FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
- NeurIPS 2026FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing
- NeurIPS 2026FlyAOC: Evaluating Agentic Ontology Curation of Drosophila Scientific Knowledge Bases
- NeurIPS 2026FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics
- NeurIPS 2026Focusing Influence Mechanism for Multi-Agent Reinforcement Learning
- NeurIPS 2026Forced Orders: What LLM Leaderboards Hide About Model Comparisons
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。