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 6 / 27 页
- NeurIPS 2026ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memory
- NeurIPS 2026Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents
- NeurIPS 2026From Chats to Markets: AgenticPay for LLM-Powered Negotiation in Multi-Agent Commerce
- NeurIPS 2026From Expert Knowledge to Optimization Modeling: Prototype-Based Data Synthesis and Logical Reinforcement Learning
- NeurIPS 2026From History to State: Constant-Context Skill Learning for LLM Agents
- NeurIPS 2026From Local Skills to Long-Horizon Tasks: Progressive Skill Exploration for LLM Web Agents
- NeurIPS 2026From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents
- NeurIPS 2026From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
- NeurIPS 2026From Representation to Intervention: Using Emotion Vectors to Monitor and Guide Language Models
- NeurIPS 2026From Talking Words to Sharing Thoughts: Scalable Multi-LLM Aggregation via Structured Message Passing
- NeurIPS 2026From Uncertain Judgments to Calibrated Rankings: Conformal Elo Estimation for LLM Evaluation
- NeurIPS 2026From Walls to Synergy: A Joint LLM-Evolution Framework for MILP Solvers
- NeurIPS 2026From Weeks to Hours: Fast and Principled SFT Curation for LLM
- NeurIPS 2026Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages
- NeurIPS 2026Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering with Generative Optimization
- NeurIPS 2026FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale
- NeurIPS 2026FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views
- NeurIPS 2026fxBench: Evaluating and Understanding Formula Suggestions in Spreadsheets
- NeurIPS 2026GCD: Correcting Hidden-State Bias in Off-Policy Agentic RL
- NeurIPS 2026Gen-Searcher: Reinforcing Agentic Search for Image Generation
- NeurIPS 2026GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators
- NeurIPS 2026Generalized Intention Modeling in Multi-Agent Reinforcement Learning
- NeurIPS 2026Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph
- NeurIPS 2026Generation Navigator: A State-Aware Agentic Framework for Image Generation
- NeurIPS 2026Generative Scenario Rollouts for End-to-End Autonomous Driving
- NeurIPS 2026GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation
- NeurIPS 2026Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice
- NeurIPS 2026Git Context Controller: Manage the Context of Agents by Agentic Git
- NeurIPS 2026GNES: Neural-Guided Evolutionary Program Search for Interpretable Multi-Agent Control
- NeurIPS 2026Gradient Boosted Trees for Retrieval-Augmented Generation
- NeurIPS 2026GraphMemRL: Action-Native Reinforcement Learning for Persistent Graph Memory Construction
- NeurIPS 2026Grounding Agent Reasoning with Structured Process Supervision for Multi-turn Reinforcement Learning
- NeurIPS 2026Group Perspective Matters: Regulating Debate Relationships Can Mitigate Blind Conformity in Multi-Agent Debate
- NeurIPS 2026Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
- NeurIPS 2026GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations
- NeurIPS 2026GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory
- NeurIPS 2026Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
- NeurIPS 2026HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models
- NeurIPS 2026Harbor Adapters and Harbor-Mix: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
- NeurIPS 2026Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents
- NeurIPS 2026HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation
- NeurIPS 2026HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV Reuse
- NeurIPS 2026HetCCL: Efficient LLM Training on Heterogeneous Vendor GPUs
- NeurIPS 2026Heterogeneous Agent Collaborative Reinforcement Learning
- NeurIPS 2026Heuresis: Evaluating Search Strategies for Autonomous Machine Learning Research Agents
- NeurIPS 2026Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking
- NeurIPS 2026Hide to Guide: Learning via Semantic Masking
- NeurIPS 2026HierFlow: Hierarchical Coupled Dual-Space Search for Automatic Agentic Workflow Generation
- NeurIPS 2026HierRR: Enhancing Instruction Alignment in Open-Vocabulary Indoor Scene Synthesis via Agentic Hierarchical Reasoning and Reflection
- NeurIPS 2026HireWatch: Evaluating LLM Compliance with U.S. Employment Law Under Contextual Pressure
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。