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 5 / 19 页
- ICML 2026Efficient Multi-round LLM Inference over Disaggregated Serving
- ICML 2026EGG: An Expert-Guided Agent Framework for Kernel Generation
- ICML 2026EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents
- ICML 2026Embodied Task Planning via Graph-Informed Action Generation with Large Language Models
- ICML 2026Emergence of Biased Consensus in Multi-Agent LLM Debates
- ICML 2026Emergent Alignment via Competition
- ICML 2026EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible Solutions
- ICML 2026EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings
- ICML 2026Envy-Free Allocation of Indivisible Goods via Noisy Queries
- ICML 2026Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning
- ICML 2026Escaping Mode Collapse in LLM Generation via Geometric Regulation
- ICML 2026Escaping Whack-a-Mole: Optimizing Documentation as Repo-Specific Playbooks for Coding Agents
- ICML 2026Estimating the Empowerment of Language Model Agents
- ICML 2026Evaluating Contextual Illegality: AI Compliance in Corporate Law Scenarios
- ICML 2026EVMbench: Evaluating AI Agents on Smart Contract Security
- ICML 2026EvoC2F: Compiling Tool Orchestration for Efficient and Evolvable LLM Agents
- ICML 2026EvoCF: Multi-Agent Collaboration via Agentic Memory-Driven Evolutionary Counterfactual Planning
- ICML 2026EvoClaw: Evaluating AI Agents on Continuous Software Evolution
- ICML 2026Evolving Interpretable Constitutions for Multi-Agent Coordination
- ICML 2026Evolving Quantitative Reasoning through Self-Play in Digital Twin Markets
- ICML 2026EVOLVING ROLLOUTS: Harnessing Historical Experience for Web Agent Evolution in Reinforcement Learning
- ICML 2026EvoMAS: Evolutionary Generation of Multi-Agent Systems
- ICML 2026EvoMAS: Heuristics in the Loop—Evolving Smarter Agentic Workflows
- ICML 2026ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation
- ICML 2026Executable Agentic Memory for GUI Agent
- ICML 2026Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic–Procedural Memory
- ICML 2026Exploration Hacking: Can LLMs Learn to Resist RL Training?
- ICML 2026FactGuard: Agentic Video Misinformation Detection via Reinforcement Learning
- ICML 2026Factored Value Functions for Graph-Based Multi-Agent Reinforcement Learning
- ICML 2026Failure is Feedback: History-Aware Backtracking for Agentic Traversal in Multimodal Graphs
- ICML 2026Failure-Driven Workflow Refinement
- ICML 2026FakeWorld 1.0: An Omni-modal Benchmark for Fake Media and Content
- ICML 2026FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights
- ICML 2026Fix Before Search: Benchmarking Agentic Visual Query Pre-processing in Multimodal Retrieval-augmented Generation
- ICML 2026FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients
- ICML 2026FlowMAP: Flow Matching for Generalizable Agent Planning
- ICML 2026FormAct: Agentic Source Editing for Rich-Format Document Generation
- ICML 2026Formalizing Learning from Language Feedback with Provable Guarantees
- ICML 2026FormalJudge: A Neuro-Symbolic Paradigm for Agentic Oversight
- ICML 2026FormulaCode: Evaluating Agentic Optimization on Large Codebases
- ICML 2026From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
- ICML 2026From Content to Knowledge: Lightning Fast Long-Video Understanding with Neural Knowledge Representations
- ICML 2026From Interaction Trajectories to Prompt Rules: Credit Assignment for Multi-Agent Prompt Optimization
- ICML 2026From Interactions to Principles: Experience-Driven Self-Distillation for Evolving LLM Agents
- ICML 2026From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training
- ICML 2026From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over Memory
- ICML 2026From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
- ICML 2026From Weak Cues to Real Identities: Evaluating Inference-Driven De-Anonymization in LLM Agents
- ICML 2026FrontierCS: Evolving Challenges for Evolving Intelligence
- ICML 2026FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents
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。