AI 智能体论文趋势 2023–2026

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。

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 1 / 17 页

1. ICLR 2026$p\textrm{-less}$ Sampling: A Robust Hyperparameter-Free Approach for LLM Decoding
2. ICLR 2026A Benchmark for Deep Information Synthesis
3. ICLR 2026A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA
4. ICLR 2026A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments
5. ICLR 2026A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning
6. ICLR 2026A$^2$Search: Ambiguity-Aware Question Answering with Reinforcement Learning
7. ICLR 2026A2ASecBench: A Protocol-Aware Security Benchmark for Agent-to-Agent Multi-Agent Systems
8. ICLR 2026ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems
9. ICLR 2026Achieving Expert-Level Agent from Foundation Model via Complexity Curriculum Reinforcement Learning with Synthetic Data
10. ICLR 2026Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
11. ICLR 2026Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning
12. ICLR 2026Advancing Multi-agent Traffic Simulation via R1-Style Reinforcement Fine-Tuning
13. ICLR 2026Aegis: Automated Error Generation and Identification for Multi-Agent Systems
14. ICLR 2026AesCoder: Code Aesthetics with Agentic Reward Feedback
15. ICLR 2026Agent Data Protocol
16. ICLR 2026Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks
17. ICLR 2026AgentFold: Long-Horizon Web Agents with Proactive Context Folding
18. ICLR 2026AgentGym-RL: An Open-Source Framework to Train LLM Agents for Long-Horizon Decision Making via Multi-Turn RL
19. ICLR 2026Agentic Collaboration as an Information Bottleneck Problem
20. ICLR 2026Agentic Context Engineering: Learning Comprehensive Contexts for Self-Improving Language Models
21. ICLR 2026Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models
22. ICLR 2026Agentic Reinforced Policy Optimization
23. ICLR 2026Agentic Reinforcement Learning with Implicit Step Rewards
24. ICLR 2026AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent
25. ICLR 2026AgentPO: Enhancing Multi-Agent Collaboration via Reinforcement Learning
26. ICLR 2026AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?
27. ICLR 2026AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents
28. ICLR 2026AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent Framework
29. ICLR 2026Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
30. ICLR 2026Alignment-Enhanced Integration of Connectivity and Spectral Sparse in Dynamic Sparse Training of LLM
31. ICLR 2026AlphaAgentEvo: Evolution-Oriented Alpha Mining via Self-Evolving Agentic Reinforcement Learning
32. ICLR 2026AlphaBench: Benchmarking Large Language Models in Formulaic Alpha Factor Mining
33. ICLR 2026AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations
34. ICLR 2026An Agentic Framework with LLMs for Solving Complex Vehicle Routing Problems
35. ICLR 2026Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven Analysis
36. ICLR 2026Analyzing and Evaluating Unbiased Language Model Watermark
37. ICLR 2026AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs
38. ICLR 2026AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite
39. ICLR 2026ATLAS: Constraints-Aware Multi-Agent Collaboration for Real-World Travel Planning
40. ICLR 2026Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test
41. ICLR 2026AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations
42. ICLR 2026AutoLibra: Agent Metric Induction from Open-Ended Human Feedback
43. ICLR 2026Automated Stateful Specialization for Adaptive Agent Systems
44. ICLR 2026AutoSP: Unlocking Long-Context LLM Training Via Compiler-Based Sequence Parallelism
45. ICLR 2026Bayesian Robust Cooperative Multi-Agent Reinforcement Learning Against Unknown Adversaries
46. ICLR 2026BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning
47. ICLR 2026BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design
48. ICLR 2026Benchmarking LLM Tool-Use in the Wild
49. ICLR 2026Benchmarking Multi-Agent Reinforcement Learning in Power Grid Operations
50. ICLR 2026Benefits and Limitations of Communication in Multi-Agent Reasoning

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。