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 8 / 27 页
- NeurIPS 2026Learning to Surpass: Training Tool-Using Agents with Anchored Feedback
- NeurIPS 2026Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance
- NeurIPS 2026Learning When to Collaborate: Selective Multi-Agent Medical Reasoning via Uncertainty-Aware Routing
- NeurIPS 2026Lemon: Evidence-Risk-Aware Adaptive Organization for Long-Horizon LLM Agents
- NeurIPS 2026LinuxArena: A Control Setting for AI Agents in Live Production Software Environments
- NeurIPS 2026LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear Payoffs
- NeurIPS 2026LLM Active Alignment: A Nash Equilibrium Perspective
- NeurIPS 2026LLM Agents Already Know When to Call Tools - Even Without Reasoning
- NeurIPS 2026LLM Routing Through the Lens of Recommendation: A Roadmap for Efficient AI Orchestration
- NeurIPS 2026LLM-ACES: Closed-Loop Discovery of Dynamic Systems with LLM-Guided Adaptive Search
- NeurIPS 2026LLM-Based Multi-Agent Blackboard System for Information Discovery in Data Science
- NeurIPS 2026LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation
- NeurIPS 2026LLMs can construct powerful representations and streamline sample-efficient supervised learning
- NeurIPS 2026LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
- NeurIPS 2026LocalAgent: Collaborative Agentic Verification for Fine-Grained Instance-Level Consistency
- NeurIPS 2026Long-Context Generation Is a Sampling Problem
- NeurIPS 2026Long-Context Language Models Require Extreme Sparsity in Context Dimension
- NeurIPS 2026LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios
- NeurIPS 2026M4Bench: Evaluating Procedural Specification for Clinical EHR Derivation Agents
- NeurIPS 2026MAGE: All-[MASK] Block Already Knows Where to Look in Block Diffusion LLM
- NeurIPS 2026MaRiO: Multi-agent Collaborative Reasoning via Shared Observations in MLLMs
- NeurIPS 2026Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems
- NeurIPS 2026Market-Based Runtime Resource Allocation for LLM Multi-Agent Systems
- NeurIPS 2026Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning
- NeurIPS 2026MASTARS: Multi-Agent Sequential Trajectory Augmentation with Return-Conditioned Subgoals
- NeurIPS 2026MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers
- NeurIPS 2026MCPHallu: Benchmarking Reasoning, Execution, and Memory Hallucinations in MCP Agents
- NeurIPS 2026MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP Agents
- NeurIPS 2026Mean-Field Control on Sparse Graphs: From Local Limits to GNNs via Neighborhood Distributions
- NeurIPS 2026Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios
- NeurIPS 2026Measuring Collapse and Correction in Homogeneous-Panel LLM Debate
- NeurIPS 2026Med-Agentic: Distilling Agentic Medical Reasoning with Internalized Meta-Capabilities
- NeurIPS 2026MedEvoEval: Evaluating Continual Evolution of Doctor Agents through Simulated Clinical Episodes
- NeurIPS 2026MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments
- NeurIPS 2026MedFlowBench: Auditing Medical Agents in Full-Study Workflows
- NeurIPS 2026MedMisBench: Measuring Epistemic Resilience of LLMs Under Misleading Medical Context
- NeurIPS 2026MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale
- NeurIPS 2026MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing
- NeurIPS 2026MemCoRe: Recovering Evidence from Progressively Compressed Factual Knowledge for Agent Memory
- NeurIPS 2026MEME: Multi-Entity & Evolving Memory Evaluation
- NeurIPS 2026MemeEconomy : Do LLM Agents Trade Ethics for Survival?
- NeurIPS 2026Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies
- NeurIPS 2026Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
- NeurIPS 2026MemPlan: Memory-Conditioned PDDL Planning for Partially Observable Text Environments
- NeurIPS 2026MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents
- NeurIPS 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
- NeurIPS 2026Mental-Models for Multi-Agent Systems
- NeurIPS 2026Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
- NeurIPS 2026Meta$^n$: Recursive Self-Improvement through Emergent Depth
- NeurIPS 2026MGMem: An Efficient, Deterministic, and Provenance-Preserving Framework for Long-Horizon Agent Memory
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。