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 3,266 篇，第 46 / 66 页
- ICML 2025Behavioral Exploration: Learning to Explore via In-Context Adaptation
- ICML 2025Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective
- ICML 2025Boosting Virtual Agent Learning and Reasoning: A Step-Wise, Multi-Dimensional, and Generalist Reward Model with Benchmark
- ICML 2025Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning
- ICML 2025BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling
- ICML 2025C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation
- ICML 2025Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression
- ICML 2025Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling
- ICML 2025Code-Generated Graph Representations Using Multiple LLM Agents for Material Properties Prediction
- ICML 2025CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective
- ICML 2025Communicating Activations Between Language Model Agents
- ICML 2025Concurrent Reinforcement Learning with Aggregated States via Randomized Least Squares Value Iteration
- ICML 2025Continuously Updating Digital Twins using Large Language Models
- ICML 2025Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning
- ICML 2025Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making
- ICML 2025Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems
- ICML 2025Cradle: Empowering Foundation Agents towards General Computer Control
- ICML 2025Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments
- ICML 2025Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination
- ICML 2025CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities
- ICML 2025Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents
- ICML 2025Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs
- ICML 2025DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy
- ICML 2025Distributionally Robust Multi-Agent Reinforcement Learning for Dynamic Chute Mapping
- ICML 2025Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning
- ICML 2025Efficient Robotic Policy Learning via Latent Space Backward Planning
- ICML 2025EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
- ICML 2025Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration
- ICML 2025Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story
- ICML 2025EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities
- ICML 2025FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems
- ICML 2025Fast Large Language Model Collaborative Decoding via Speculation
- ICML 2025Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field Games
- ICML 2025Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning
- ICML 2025Fleet of Agents: Coordinated Problem Solving with Large Language Models
- ICML 2025Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options
- ICML 2025From Debate to Equilibrium: Belief‑Driven Multi‑Agent LLM Reasoning via Bayesian Nash Equilibrium
- ICML 2025From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
- ICML 2025G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks
- ICML 2025General agents need world models
- ICML 2025GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation
- ICML 2025GradPS: Resolving Futile Neurons in Parameter Sharing Network for Multi-Agent Reinforcement Learning
- ICML 2025Graph Diffusion for Robust Multi-Agent Coordination
- ICML 2025Graph World Model
- ICML 2025Gravity-Bench-v1: A Benchmark on Gravitational Physics Discovery for Agents
- ICML 2025GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning
- ICML 2025Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents
- ICML 2025Hidden No More: Attacking and Defending Private Third-Party LLM Inference
- ICML 2025Hybrid Quantum-Classical Multi-Agent Pathfinding
- ICML 2025HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning
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。