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 947 篇，第 16 / 19 页
- ICML 2025PaperBench: Evaluating AI’s Ability to Replicate AI Research
- ICML 2025PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification
- ICML 2025PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation
- ICML 2025PINNsAgent: Automated PDE Surrogation with Large Language Models
- ICML 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
- ICML 2025PokéChamp: an Expert-level Minimax Language Agent
- ICML 2025Policy-Regret Minimization in Markov Games with Function Approximation
- ICML 2025Position: AI Agents Need Authenticated Delegation
- ICML 2025Position: Build Agent Advocates, Not Platform Agents
- ICML 2025Position: LLM Social Simulations Are a Promising Research Method
- ICML 2025Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives
- ICML 2025Position: The Most Expensive Part of an LLM *should* be its Training Data
- ICML 2025Position: Theory of Mind Benchmarks are Broken for Large Language Models
- ICML 2025Position: Truly Self-Improving Agents Require Intrinsic Metacognitive Learning
- ICML 2025Position: Uncertainty Quantification Needs Reassessment for Large Language Model Agents
- ICML 2025Position: We Need An Algorithmic Understanding of Generative AI
- ICML 2025Prediction-Aware Learning in Multi-Agent Systems
- ICML 2025Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents
- ICML 2025Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty
- ICML 2025Proposer-Agent-Evaluator (PAE): Autonomous Skill Discovery For Foundation Model Internet Agents
- ICML 2025Provably Efficient Algorithm for Best Scoring Rule Identification in Online Principal-Agent Information Acquisition
- ICML 2025Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction
- ICML 2025QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search
- ICML 2025R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning
- ICML 2025RE-Bench: Evaluating Frontier AI R&D Capabilities of Language Model Agents against Human Experts
- ICML 2025Reflection-Bench: Evaluating Epistemic Agency in Large Language Models
- ICML 2025Reidentify: Context-Aware Identity Generation for Contextual Multi-Agent Reinforcement Learning
- ICML 2025Reinforce LLM Reasoning through Multi-Agent Reflection
- ICML 2025RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing
- ICML 2025ResearchTown: Simulator of Human Research Community
- ICML 2025Revisiting Cooperative Off-Policy Multi-Agent Reinforcement Learning
- ICML 2025Risk-Sensitive Theory of Mind: Coordinating with Agents of Unknown Bias using Cumulative Prospect Theory
- ICML 2025RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning
- ICML 2025Robust Multi-Agent Reinforcement Learning with Stochastic Adversary
- ICML 2025Robust Multi-bit Text Watermark with LLM-based Paraphrasers
- ICML 2025Robust Noise Attenuation via Adaptive Pooling of Transformer Outputs
- ICML 2025Sable: a Performant, Efficient and Scalable Sequence Model for MARL
- ICML 2025SafeArena: Evaluating the Safety of Autonomous Web Agents
- ICML 2025Self-Play $Q$-Learners Can Provably Collude in the Iterated Prisoner's Dilemma
- ICML 2025ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
- ICML 2025Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models
- ICML 2025Solving Zero-Sum Convex Markov Games
- ICML 2025Star Attention: Efficient LLM Inference over Long Sequences
- ICML 2025StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models
- ICML 2025SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training
- ICML 2025SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
- ICML 2025SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering
- ICML 2025Synthesizing Software Engineering Data in a Test-Driven Manner
- ICML 2025The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models
- ICML 2025The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
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。