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 500 篇，第 5 / 10 页
- ICLR 2026ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases
- ICLR 2026Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations
- ICLR 2026Improving Code Localization with Repository Memory
- ICLR 2026Improving Human-AI Coordination through Online Adversarial Training and Generative Models
- ICLR 2026In Agents We Trust, but Who Do Agents Trust? Latent Preferences Steer LLM Generations
- ICLR 2026In-The-Flow Agentic System Optimization for Effective Planning and Tool Use
- ICLR 2026Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning
- ICLR 2026Influence-Preserving Proxies for Gradient-Based Data Selection in LLM FineTuning
- ICLR 2026InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents
- ICLR 2026Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM Agents
- ICLR 2026InnoGym: Benchmarking the Innovation Potential of AI Agents
- ICLR 2026InnovatorBench: Evaluating Agents’ Ability to Conduct Innovative AI Research
- ICLR 2026InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search
- ICLR 2026Inter-Agent Relative Representations for Multi-Agent Option Discovery
- ICLR 2026Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval
- ICLR 2026Interactive Agents to Overcome Underspecificity in Software Engineering
- ICLR 2026IR-Agent: Expert-Inspired LLM Agents for Structure Elucidation from Infrared Spectra
- ICLR 2026IterResearch: Rethinking Long-Horizon Agents via Markovian State Reconstruction
- ICLR 2026JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks
- ICLR 2026Jet Expansions: Restructuring LLM Computation for Model Inspection
- ICLR 2026JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generation
- ICLR 2026Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
- ICLR 2026K²-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device Control
- ICLR 2026Kimi-Dev: Agentless Training as Skill Prior for SWE-agents
- ICLR 2026KnowGuard: Knowledge-Driven Abstention for Multi-Round Clinical Reasoning
- ICLR 2026KRAMABENCH: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes
- ICLR 2026KVComm: Enabling Efficient LLM Communication through Selective KV Sharing
- ICLR 2026Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
- ICLR 2026Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text
- ICLR 2026Learning Efficient and Interpretable Multi-Agent Communication
- ICLR 2026Learning Global Hypothesis Space for Enhancing Synergistic Reasoning Chain
- ICLR 2026Learning to Orchestrate Agents in Natural Language with the Conductor
- ICLR 2026Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training
- ICLR 2026Learning to Summarize by Learning to Quiz: Adversarial Agentic Collaboration for Long Document Summarization
- ICLR 2026LeSTD: LLM Compression via Learning-based Sparse Tensor Decomposition
- ICLR 2026Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification
- ICLR 2026LH-DECEPTION: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions
- ICLR 2026LiveResearchBench: Benchmarking Single- and Multi-Agent Systems for Citation-Grounded Deep Research
- ICLR 2026LiveWeb-IE: A Benchmark For Online Web Information Extraction
- ICLR 2026LLM DNA: Tracing Model Evolution via Functional Representations
- ICLR 2026LLM Fingerprinting via Semantically Conditioned Watermarks
- ICLR 2026LLM Unlearning with LLM Beliefs
- ICLR 2026LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures
- ICLR 2026LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities
- ICLR 2026LLMs Get Lost In Multi-Turn Conversation
- ICLR 2026lmgame-Bench: How Good are LLMs at Playing Games?
- ICLR 2026LoC-Decomp: LLM Autoformalization via Logical Concept Decomposition and Iterative Feedback Correction
- ICLR 2026Log Probability Tracking of LLM APIs
- ICLR 2026Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation
- ICLR 2026LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision
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。