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 10 / 15 页
- NeurIPS 2026Open-Ended Scientific Discovery and the Social Dynamics of Evolving Agent Networks
- NeurIPS 2026OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
- NeurIPS 2026OpenSearcher: Democratizing Deep Search through a Fully Offline Pipeline with Programmatic Verification
- NeurIPS 2026Optimal Contextual Pricing under Agnostic Non-Lipschitz Demand
- NeurIPS 2026Optimize Once, Execute Fast: Latency-Aware Multi-Agent Workflow Learning for Recurrent Queries
- NeurIPS 2026Optimizing Agent Tool-Use via Trajectory-based Insight Evolution
- NeurIPS 2026Optimizing Analytic Constants via AI-Guided Lean Proof Refinement
- NeurIPS 2026OrchestraRL: Learning to Orchestrate LLM Agent Swarms with Entropy-Aware Communication Control
- NeurIPS 2026OS-Omni: A Cross-Platform Benchmark for Generalist Computer-Using Agents
- NeurIPS 2026Overcoming Attention Distraction: Training-Free Latent Communication for Multi-Agent Systems
- NeurIPS 2026Overthinking as a Symptom of Knowledge Conflict: Understanding and Detecting LLM's Hallucinations in Retrieval-Augmented Question Answering
- NeurIPS 2026P$^{3}$: Joint Program-and-Proof Planning\\ for Verified Code Generation
- NeurIPS 2026Pacing Branch Parallelism in LLM Serving
- NeurIPS 2026PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
- NeurIPS 2026ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
- NeurIPS 2026PatchScout: Thematic Web Data Collection via Information Foraging
- NeurIPS 2026PatternBloom: Empowering Agentic RAG with Externalized RL-Distilled Graph Patterns
- NeurIPS 2026PBT-Bench: Benchmarking AI Agents on Property-Based Testing
- NeurIPS 2026PCBInnoBench: Benchmarking LLM Agents on Real-World PCB Design
- NeurIPS 2026PCFBench: How Far Can Large Vision-Language Models Go in Physics-aware Photonic Inverse Design?
- NeurIPS 2026PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents
- NeurIPS 2026Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-Horizon Agents
- NeurIPS 2026PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning
- NeurIPS 2026PhysAgentGym: Free Physical-Law Verifiers for Training Small Code-Reasoning Agents
- NeurIPS 2026PiCA: Pivot-Based Credit Assignment For Search Agentic Reinforcement Learning
- NeurIPS 2026PieArena: Ranking and Profiling Language Agents in Realistic Negotiation Scenarios
- NeurIPS 2026PithTrain: A Compact and Agent-Native MoE Training System
- NeurIPS 2026PIVOT: A Unified Agentic Framework for Streaming Long-Video Understanding
- NeurIPS 2026PLATO: Pointer Learner for Agent and Task Openness
- NeurIPS 2026Playing Markov Games Without Observing Payoffs
- NeurIPS 2026Policy-Level Exploration for Coordinated Multi-Agent Reinforcement Learning
- NeurIPS 2026Population-Aligned Persona Generation for LLM-based Social Simulation
- NeurIPS 2026Position: A Safe LLM and a Safe Harness Do Not Make a Safe Agent
- NeurIPS 2026Position: Machine Learning Conferences Should Introduce an Autonomous Research Track
- NeurIPS 2026Posterior Sampling-based Online Learning for Episodic POMDPs
- NeurIPS 2026Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning
- NeurIPS 2026Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?
- NeurIPS 2026PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents
- NeurIPS 2026Predicting What Changes: Causal Delta World Models for Risk-Aware LLM Agent Planning
- NeurIPS 2026Prefix Executability: Evaluating Tool-Using Agents Beyond Final Success
- NeurIPS 2026Preventing Error Cascades in Long-Horizon Multimodal Agents with Edge-Reliability Graph Memory
- NeurIPS 2026Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design
- NeurIPS 2026PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents
- NeurIPS 2026ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts
- NeurIPS 2026Profit Maximization in Bilateral Trade against a Smooth Adversary
- NeurIPS 2026ProGraf: Profile-Guided Planning for Step-by-Step Generation of Structured Non-Natural Images
- NeurIPS 2026ProgramBench: Can Language Models Rebuild Programs From Scratch?
- NeurIPS 2026Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents
- NeurIPS 2026Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble
- NeurIPS 2026Proper Scoring Rules for Agentic Uncertainty Quantification
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。