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 1,983 篇，第 15 / 40 页
- ICML 2026Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at Scale
- ICML 2026Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information
- ICML 2026Beyond Static Endpoints: Tool Programs as an Interface for Flexible Agentic Web Services
- ICML 2026Beyond Text-to-SQL: Can LLMs Really Debug Enterprise ETL SQL?
- ICML 2026Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
- ICML 2026Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning
- ICML 2026BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics
- ICML 2026BIOARC: Discovering Optimal Neural Architectures for Biological Foundation Models
- ICML 2026Bootstrapped Exploration with Causal Reasoning: A Training Paradigm for Adaptive Forecasting Agent
- ICML 2026Bridging Functional Correctness and Runtime Efficiency Gaps in LLM-Based Code Translation
- ICML 2026Bridging the Grounding Gap in VideoQA via Typed Memory for Language-based Belief-State Reasoning
- ICML 2026BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs
- ICML 2026Budget-Efficient Attacks and Robustness Training for Cooperative MARL
- ICML 2026BuildArena: A Physics-Aligned Interactive Benchmark of LLMs for Engineering Construction
- ICML 2026Calibrating Conservatism for Scalable Oversight
- ICML 2026Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use
- ICML 2026Can LLM Agents Stick to the Script? Modeling Commitment in Interactive Narratives
- ICML 2026CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training
- ICML 2026CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments
- ICML 2026Catch-22: On the Fundamental Tradeoff Between Detectability and Robustness in LLM Watermarking
- ICML 2026Causal Detection of Multi-Step LLM Agent Attacks
- ICML 2026CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution
- ICML 2026CausalGame: Benchmarking Causal Thinking of LLM Agents in Games
- ICML 2026CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception
- ICML 2026CCLRec: Consensus-driven Contrastive Learning for LLM-enhanced Graph Recommendation
- ICML 2026CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding
- ICML 2026CGRiC: Compositional Risk Certification for Structured LLM Outputs
- ICML 2026Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
- ICML 2026Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models
- ICML 2026CINOC: Cardinality-Invariant Neural Operator Policies for Scalable PDE Control
- ICML 2026Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation
- ICML 2026CLIMB: Taming the LoRA Residency Cliff in Multi-LoRA Serving
- ICML 2026Clipping Low-Probability Tokens in SFT Yields a Generalizable Initialization for RL
- ICML 2026Closing the Expression Gap in LLM Instructions via Socratic Questioning
- ICML 2026Closing the Loop: Universal Repository Representation with RPG-Encoder
- ICML 2026Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents
- ICML 2026CocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcement Learning
- ICML 2026CoDA-Bench: Can Code Agents Handle Data-Intensive Tasks?
- ICML 2026Code2Video: A Code-centric Paradigm for Educational Video Creation
- ICML 2026Code2Worlds: Empowering Coding LLMs for 4D World Generation
- ICML 2026CodeTaste: Can LLMs Generate Human-Level Code Refactorings?
- ICML 2026CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement
- ICML 2026Collaborative Disagreement Resolution for Scalable Oversight
- ICML 2026CoME: Empowering Channel-of-Mobile-Experts with Informative Hybrid-Capabilities Reasoning
- ICML 2026CoMem: Context Management with A Decoupled Long-Context Model
- ICML 2026ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox
- ICML 2026CONCUR: High-Throughput Agentic Batch Inference of LLM via Congestion-Based Concurrency Control
- ICML 2026Conflict-Aware Adaptive Alignment for LLM Hallucination Mitigation
- ICML 2026ConServe: Fine-Grained GPU Harvesting for LLM Online and Offline Co-Serving
- ICML 2026Constitutional Black-Box Monitoring for Scheming in LLM Agents
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。