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 24 / 66 页
- ICML 2026Sparse Topology-Aware Pairwise Scoring for Large-Scale Multi-Agent Reinforcement Learning
- ICML 2026Speculative Safety Honeypot: Toward Proactive Defense Against Multi-turn Agent Attacks
- ICML 2026Sponge Tool Attack: Stealthy Denial-of-Efficiency against Tool-Augmented Agentic Reasoning
- ICML 2026SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning
- ICML 2026StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning
- ICML 2026Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games
- ICML 2026Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
- ICML 2026Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents
- ICML 2026Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
- ICML 2026Structurally Aligned Subtask-Level Memory for Software Engineering Agents
- ICML 2026Student-Centered Distillation Narrows the Agentic Gap Between Small and Large LLMs
- ICML 2026SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark
- ICML 2026SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
- ICML 2026SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models
- ICML 2026SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents
- ICML 2026Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs
- ICML 2026T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning
- ICML 2026TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning
- ICML 2026TadA-Bench: A Million-Variant Benchmark for Future-Round Discovery Toward Agentic Protein Engineering
- ICML 2026Talk, Judge, Cooperate: Gossip-Driven Indirect Reciprocity in Self-Interested LLM Agents
- ICML 2026Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework
- ICML 2026Task-Awareness Improves LLM Generations and Uncertainty
- ICML 2026TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination
- ICML 2026TestExplora: Benchmarking LLMs for Proactive Bug Discovery via Repository-Level Test Generation
- ICML 2026Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding
- ICML 2026TextResNet: Decoupling and Routing Optimization Signals in Compound AI Systems via Deep Residual Tuning
- ICML 2026TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems
- ICML 2026The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works
- ICML 2026The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind
- ICML 2026The Deterministic Horizon: When Extended Reasoning Fails and Tool Delegation Becomes Necessary
- ICML 2026The First Drop of Ink: Nonlinear Impact of Misleading Information in Long-Context Reasoning
- ICML 2026The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy
- ICML 2026The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design
- ICML 2026The Truth Stays in the Family: Enhancing Contextual Truthfulness via Inherited Heads in Model Lineages
- ICML 2026The Value of Variance: Mitigating Debate Collapse in Multi-Agent Systems via Uncertainty-Driven Policy Optimization
- ICML 2026Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents
- ICML 2026Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning
- ICML 2026Threat2Traffic: Multi-Agent Environment Synthesis for Malware Traffic Generation from Threat Intelligence
- ICML 2026Threshold-Based Exclusive Batching for LLM Inference
- ICML 2026ThunderAgent: A Fast, Simple, and Program-Aware Agentic Inference System
- ICML 2026TileSparse: Arithmetic-Intensity-Aware Sparse Attention for Compute-Bound LLM Decoding
- ICML 2026TodoEvolve: Learning to Architect Agent Planning Systems
- ICML 2026Token-Level LLM Collaboration via FusionRoute
- ICML 2026TOM-SWE: User Mental Modeling For Software Engineering Agents
- ICML 2026ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind
- ICML 2026ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
- ICML 2026Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning
- ICML 2026Toward Training Superintelligent Software Agents through Self-Play SWE-RL
- ICML 2026Towards a Science of AI Agent Reliability
- ICML 2026Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis
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。