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 1,317 篇，第 1 / 27 页

1. NeurIPS 2026$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
2. NeurIPS 2026$\chi$-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
3. NeurIPS 20262-Step Agent: How a Bayesian Decision Maker Learns from AI-Decision Support
4. NeurIPS 20263DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code
5. NeurIPS 2026A Benchmark for Omni-Modal Reasoning in Long Videos
6. NeurIPS 2026A Communication-Theoretic Framework for LLM Agents: Cost-Aware Adaptive Reliability
7. NeurIPS 2026A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training
8. NeurIPS 2026A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
9. NeurIPS 2026A Stratified Multi-Rater Evaluation of LLM-Based Virtual Standardized Patients with a Deployed Data-Generation Platform
10. NeurIPS 2026A Structured LLM Framework for Inorganic Material Synthesis Planning
11. NeurIPS 2026A Unifying View of Anchoring via Operator-Side Tikhonov Regularization
12. NeurIPS 2026A2Eval: Agentic and Automated Evaluation for Embodied Brain
13. NeurIPS 2026ABHBench: Evaluating Moral Decision-Making of Foundation Models from an Agentic Perspective
14. NeurIPS 2026ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence
15. NeurIPS 2026Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique
16. NeurIPS 2026AdaM-Rec: Adaptive Modality Routing for Multimodal Recommendation
17. NeurIPS 2026AdaMAP: Learning Adaptive Multi-Action Prediction with Grounded Dreaming Guidance
18. NeurIPS 2026Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security
19. NeurIPS 2026Adaptive auditing of AI systems with anytime-valid guarantees
20. NeurIPS 2026Adaptive Communication Range for Scalable Cooperative Multi-Agent Reinforcement Learning
21. NeurIPS 2026Adaptive Fine-Tuning Scheduler for Multi-Tenant Edge LLM via Convergence-Aware Bandits
22. NeurIPS 2026Adaptive LLM Routing for Multi-Turn Conversations with Continuously Evolving User Queries
23. NeurIPS 2026AdaptNC: Adaptive Nonconformity Scores for Conformal Prediction under Distribution Shift
24. NeurIPS 2026AdaWM: Few-Shot Adaptation of World Models to Unseen Dynamical Regimes
25. NeurIPS 2026Addressing Exogenous Variability in Cooperative Multi-Agent Reinforcement Learning
26. NeurIPS 2026ADMIT: Support-Gated Memory-Write Admission for Document QA Agents
27. NeurIPS 2026Adversarially Attacking Symbolic Vocabulary Vulnerabilities In LLM Planners
28. NeurIPS 2026AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning
29. NeurIPS 2026Agent Explorative Policy Optimization for Agentic Multimodal Reasoning
30. NeurIPS 2026Agent MechSuits : Mechanistic Subspace Safety Steering for Multi-Turn CLI Agents
31. NeurIPS 2026Agent-ToM: Learning to Monitor Autonomous LLM Agents via Theory-of-Mind Reasoning
32. NeurIPS 2026Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback
33. NeurIPS 2026AgentAbstain: Do LLM Agents Know When Not to Act?
34. NeurIPS 2026AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent
35. NeurIPS 2026AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators
36. NeurIPS 2026AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
37. NeurIPS 2026AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Scientific Question Answering
38. NeurIPS 2026Agentic Abstention: Do Agents Know When to Stop Instead of Act?
39. NeurIPS 2026Agentic AI Design Should be Mediated to Promote Social Welfare
40. NeurIPS 2026Agentic Geometry Problem Solving via Human-like Parallel Bidirectional Reasoning
41. NeurIPS 2026Agentic Multi-Turn Reasoning: A Fairness Approach
42. NeurIPS 2026Agentic Neural Architecture Search
43. NeurIPS 2026Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction
44. NeurIPS 2026Agentic-imodels: Evolving agentic interpretability tools via autoresearch
45. NeurIPS 2026Agentick: A Unified Benchmark for General Sequential Decision-Making Agents
46. NeurIPS 2026AgenticVBench: Can AI Agents Complete Real-World Video Production Tasks?
47. NeurIPS 2026AgentKernelArena: Benchmarking Performance and Generalization of AI Coding Agents on GPU Kernels Optimization
48. NeurIPS 2026AgenTracer-v2: Agentic Failure Tracer for LLM Agentic Systems
49. NeurIPS 2026AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace
50. NeurIPS 2026Agents as Neuro-Symbolic Reasoners: Path Feasibility Reasoning for Precise Static Bug Detection

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。