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 817 篇，第 14 / 17 页
- ICLR 2025PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks
- ICLR 2025PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration
- ICLR 2025POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding
- ICLR 2025Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation
- ICLR 2025Preble: Efficient Distributed Prompt Scheduling for LLM Serving
- ICLR 2025Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
- ICLR 2025Rational Decision-Making Agent with Learning Internal Utility Judgment
- ICLR 2025Re-Aligning Language to Visual Objects with an Agentic Workflow
- ICLR 2025Reconstruction-Guided Policy: Enhancing Decision-Making through Agent-Wise State Consistency
- ICLR 2025RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code
- ICLR 2025Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
- ICLR 2025Reward Learning from Multiple Feedback Types
- ICLR 2025Robotouille: An Asynchronous Planning Benchmark for LLM Agents
- ICLR 2025Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning
- ICLR 2025ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL
- ICLR 2025Scaling Autonomous Agents via Automatic Reward Modeling And Planning
- ICLR 2025Scaling Large Language Model-based Multi-Agent Collaboration
- ICLR 2025ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
- ICLR 2025SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents
- ICLR 2025Self-Evolving Multi-Agent Collaboration Networks for Software Development
- ICLR 2025ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents
- ICLR 2025Simulating Human-like Daily Activities with Desire-driven Autonomy
- ICLR 2025Single-agent Poisoning Attacks Suffice to Ruin Multi-Agent Learning
- ICLR 2025SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION
- ICLR 2025Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows
- ICLR 2025Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports
- ICLR 2025SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget
- ICLR 2025STAMP: Scalable Task- And Model-agnostic Collaborative Perception
- ICLR 2025Steering Large Language Models between Code Execution and Textual Reasoning
- ICLR 2025Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function Approximation
- ICLR 2025Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search
- ICLR 2025SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement
- ICLR 2025Systems with Switching Causal Relations: A Meta-Causal Perspective
- ICLR 2025TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
- ICLR 2025Tool-Planner: Task Planning with Clusters across Multiple Tools
- ICLR 2025ToolACE: Winning the Points of LLM Function Calling
- ICLR 2025ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Models
- ICLR 2025ToolGen: Unified Tool Retrieval and Calling via Generation
- ICLR 2025TorchTitan: One-stop PyTorch native solution for production ready LLM pretraining
- ICLR 2025Toward Efficient Multi-Agent Exploration With Trajectory Entropy Maximization
- ICLR 2025Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
- ICLR 2025Tractable Multi-Agent Reinforcement Learning through Behavioral Economics
- ICLR 2025Trajectory-Class-Aware Multi-Agent Reinforcement Learning
- ICLR 2025Trajectory-LLM: A Language-based Data Generator for Trajectory Prediction in Autonomous Driving
- ICLR 2025Triples as the Key: Structuring Makes Decomposition and Verification Easier in LLM-based TableQA
- ICLR 2025Video Action Differencing
- ICLR 2025VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks
- ICLR 2025Visual Agents as Fast and Slow Thinkers
- ICLR 2025VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents
- ICLR 2025Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation
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。