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

每年论文数

各会议论文数

按年份和会议统计

AI 智能体论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202376404113170
2024150738818329
202536220417840784
20267295006401141,983

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

全部AI 智能体论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 784 篇，第 3 / 16 页

  1. ICLR 2025DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace Editing
  2. ICLR 2025DS-LLM: Leveraging Dynamical Systems to Enhance Both Training and Inference of Large Language Models
  3. ICLR 2025DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?
  4. ICLR 2025DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity
  5. ICLR 2025EFFICIENT JAILBREAK ATTACK SEQUENCES ON LARGE LANGUAGE MODELS VIA MULTI-ARMED BANDIT-BASED CONTEXT SWITCHING
  6. ICLR 2025Efficient Multi-agent Offline Coordination via Diffusion-based Trajectory Stitching
  7. ICLR 2025Efficiently Parameterized Neural Metriplectic Systems
  8. ICLR 2025EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE
  9. ICLR 2025EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents
  10. ICLR 2025Empowering LLM Agents with Zero-Shot Optimal Decision-Making through Q-learning
  11. ICLR 2025Empowering Users in Digital Privacy Management through Interactive LLM-Based Agents
  12. ICLR 2025Encryption-Friendly LLM Architecture
  13. ICLR 2025Enhancing Language Model Agents using Diversity of Thoughts
  14. ICLR 2025eQMARL: Entangled Quantum Multi-Agent Reinforcement Learning for Distributed Cooperation over Quantum Channels
  15. ICLR 2025ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning
  16. ICLR 2025Expected Return Symmetries
  17. ICLR 2025Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank
  18. ICLR 2025Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View
  19. ICLR 2025Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning
  20. ICLR 2025Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning
  21. ICLR 2025FlickerFusion: Intra-trajectory Domain Generalizing Multi-agent Reinforcement Learning
  22. ICLR 2025Flow: Modularized Agentic Workflow Automation
  23. ICLR 2025Fourier Head: Helping Large Language Models Learn Complex Probability Distributions
  24. ICLR 2025From an LLM Swarm to a PDDL-empowered Hive: Planning Self-executed Instructions in a Multi-modal Jungle
  25. ICLR 2025From Commands to Prompts: LLM-based Semantic File System for AIOS
  26. ICLR 2025Generalized Principal-Agent Problem with a Learning Agent
  27. ICLR 2025Generating Freeform Endoskeletal Robots
  28. ICLR 2025GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS
  29. ICLR 2025Graph Neural Networks Gone Hogwild
  30. ICLR 2025GraphRouter: A Graph-based Router for LLM Selections
  31. ICLR 2025GROOT-2: Weakly Supervised Multimodal Instruction Following Agents
  32. ICLR 2025Human Simulacra: Benchmarking the Personification of Large Language Models
  33. ICLR 2025Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models
  34. ICLR 2025ImProver: Agent-Based Automated Proof Optimization
  35. ICLR 2025Improving Data Efficiency via Curating LLM-Driven Rating Systems
  36. ICLR 2025INS: Interaction-aware Synthesis to Enhance Offline Multi-agent Reinforcement Learning
  37. ICLR 2025InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation
  38. ICLR 2025Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models
  39. ICLR 2025Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface
  40. ICLR 2025Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence
  41. ICLR 2025IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning
  42. ICLR 2025Inverse Attention Agents for Multi-Agent Systems
  43. ICLR 2025InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma
  44. ICLR 2025IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities
  45. ICLR 2025IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking
  46. ICLR 2025JudgeBench: A Benchmark for Evaluating LLM-Based Judges
  47. ICLR 2025Language Agents Meet Causality -- Bridging LLMs and Causal World Models
  48. ICLR 2025Learn-by-interact: A Data-Centric Framework For Self-Adaptive Agents in Realistic Environments
  49. ICLR 2025Learning Dynamics of LLM Finetuning
  50. ICLR 2025Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation

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"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「前沿系统」下的其他主题