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 3,266 篇，第 42 / 66 页

  1. ICLR 2025Benchmarking Agentic Workflow Generation
  2. ICLR 2025Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback
  3. ICLR 2025BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments
  4. ICLR 2025Breaking Mental Set to Improve Reasoning through Diverse Multi-Agent Debate
  5. ICLR 2025Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
  6. ICLR 2025Can Textual Gradient Work in Federated Learning?
  7. ICLR 2025Can Watermarks be Used to Detect LLM IP Infringement For Free?
  8. ICLR 2025Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems
  9. ICLR 2025CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation
  10. ICLR 2025CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL
  11. ICLR 2025ChemAgent: Self-updating Memories in Large Language Models Improves Chemical Reasoning
  12. ICLR 2025CofCA: A STEP-WISE Counterfactual Multi-hop QA benchmark
  13. ICLR 2025Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
  14. ICLR 2025ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization
  15. ICLR 2025Combatting Dimensional Collapse in LLM Pre-Training Data via Submodular File Selection
  16. ICLR 2025COMBO: Compositional World Models for Embodied Multi-Agent Cooperation
  17. ICLR 2025Competing Large Language Models in Multi-Agent Gaming Environments
  18. ICLR 2025Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems
  19. ICLR 2025Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models
  20. ICLR 2025DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback
  21. ICLR 2025DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference
  22. ICLR 2025DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory
  23. ICLR 2025Digi-Q: Learning VLM Q-Value Functions for Training Device-Control Agents
  24. ICLR 2025Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Model Using Implicit Feedback from Pre-training Demonstrations
  25. ICLR 2025Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control
  26. ICLR 2025Discriminator-Guided Embodied Planning for LLM Agent
  27. ICLR 2025Dissecting Adversarial Robustness of Multimodal LM Agents
  28. ICLR 2025DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agent
  29. ICLR 2025Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents
  30. ICLR 2025Do as We Do, Not as You Think: the Conformity of Large Language Models
  31. ICLR 2025Do LLM Agents Have Regret? A Case Study in Online Learning and Games
  32. ICLR 2025Do LLMs ``know'' internally when they follow instructions?
  33. ICLR 2025DoF: A Diffusion Factorization Framework for Offline Multi-Agent Reinforcement Learning
  34. ICLR 2025DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace Editing
  35. ICLR 2025DS-LLM: Leveraging Dynamical Systems to Enhance Both Training and Inference of Large Language Models
  36. ICLR 2025DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?
  37. ICLR 2025DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity
  38. ICLR 2025EFFICIENT JAILBREAK ATTACK SEQUENCES ON LARGE LANGUAGE MODELS VIA MULTI-ARMED BANDIT-BASED CONTEXT SWITCHING
  39. ICLR 2025Efficient Multi-agent Offline Coordination via Diffusion-based Trajectory Stitching
  40. ICLR 2025Efficiently Parameterized Neural Metriplectic Systems
  41. ICLR 2025EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE
  42. ICLR 2025EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents
  43. ICLR 2025Empowering LLM Agents with Zero-Shot Optimal Decision-Making through Q-learning
  44. ICLR 2025Empowering Users in Digital Privacy Management through Interactive LLM-Based Agents
  45. ICLR 2025Encryption-Friendly LLM Architecture
  46. ICLR 2025Enhancing Language Model Agents using Diversity of Thoughts
  47. ICLR 2025eQMARL: Entangled Quantum Multi-Agent Reinforcement Learning for Distributed Cooperation over Quantum Channels
  48. ICLR 2025ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning
  49. ICLR 2025Expected Return Symmetries
  50. ICLR 2025Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank

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