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 40 / 40 页
- NeurIPS 2026Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
- NeurIPS 2026VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic Model
- NeurIPS 2026Visual Harness: Grounding Multimodal Reasoning in Physics Engines
- NeurIPS 2026Vortex: Efficient and Programmable Sparse Attention Serving
- NeurIPS 2026Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games
- NeurIPS 2026What Claims Do LLM Benchmark Scores Support?
- NeurIPS 2026What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents
- NeurIPS 2026What Makes Two States the Same? Value-Aware State Matching for Multi-Turn Agent Credit Assignment
- NeurIPS 2026What Should Remain After Forgetting? Rethinking LLM Unlearning as Predictive Posterior Correction
- NeurIPS 2026What Stops SGD on LLM Pre-Training: The Need for Large Learning Rate and How to Achieve it
- NeurIPS 2026When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?
- NeurIPS 2026When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning
- NeurIPS 2026When Do Multi-Agent Systems Help? An Information Bottleneck Perspective
- NeurIPS 2026When Expert Disagreement Hurts: Auditing Prestige-Sensitive Revision in LLM Decision Pipelines
- NeurIPS 2026When Further Realization Is Unnecessary: Amortized Reasoning for Long-Horizon LLM Agents
- NeurIPS 2026When LLM Routers Overpay: Strong-Model Over-Selection under Loose Budgets
- NeurIPS 2026When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding
- NeurIPS 2026When the Most Disruptive Messages Are Safe to Prune in Aggregate: Functional Analysis of Communication Pruning in Two-Agent LLM Systems
- NeurIPS 2026Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers
- NeurIPS 2026Who Should Evolve? Uncertainty-Aware Role Bottleneck Inference for Multi-Agent LLM Training
- NeurIPS 2026Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?
- NeurIPS 2026Why Copy Others? Insights into Social Learning from Multi-Agent Reinforcement Learning
- NeurIPS 2026WiREBench: Evaluating AI Agents' Capabilities in Reverse-Engineering Black-Box Applications in the Real World
- NeurIPS 2026Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies
- NeurIPS 2026World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning
- NeurIPS 2026WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction
- NeurIPS 2026WURI: Watching Unfolding Risk in Agent Interactions
- NeurIPS 2026XBRIDGE: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication
- NeurIPS 2026XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity
- NeurIPS 2026Youdunit: Single-Call Counterfactual Necessity in Multi-Agent LLM Systems
- NeurIPS 2026ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration
- NeurIPS 2026Zero-Shot Coordination among LLM Agents
- NeurIPS 2026Zero-Violation Regret for Cooperative Markov Games with Coupled Instantaneous Hard Constraints
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。