AI Agents papers, 2023–2026

Key findings

• AI Agents went from 170 papers in 2023 to 1,983 in 2026, roughly 12x in three years.
• NeurIPS publishes the most AI Agents work: 1,317 papers from 2023 to 2026, 40% of the four-venue total.
• The fastest-growing overlap is with LLM Benchmarks: papers tagged with both rose from 1 in 2023 to 116 in 2026.
• Among the 4 topics under Trending Systems, it ranks #2 by 2026 paper count; the fastest grower in the group, World Models, is up 11x versus 12x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All AI Agents papers

1,317 papers, page 21 of 27

1001. NeurIPS 2025Representation Consistency for Accurate and Coherent LLM Answer Aggregation
1002. NeurIPS 2025Retro-R1: LLM-based Agentic Retrosynthesis
1003. NeurIPS 2025RF-Agent: Automated Reward Function Design via Language Agent Tree Search
1004. NeurIPS 2025RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
1005. NeurIPS 2025RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills
1006. NeurIPS 2025Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
1007. NeurIPS 2025Role-aware Multi-agent Reinforcement Learning for Coordinated Emergency Traffic Control
1008. NeurIPS 2025SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
1009. NeurIPS 2025Sample-Efficient Tabular Self-Play for Offline Robust Reinforcement Learning
1010. NeurIPS 2025Scalable Neural Incentive Design with Parameterized Mean-Field Approximation
1011. NeurIPS 2025Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis
1012. NeurIPS 2025SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent
1013. NeurIPS 2025SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
1014. NeurIPS 2025SE-GUI: Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning
1015. NeurIPS 2025SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks
1016. NeurIPS 2025Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition
1017. NeurIPS 2025SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents
1018. NeurIPS 2025Seeking and Updating with Live Visual Knowledge
1019. NeurIPS 2025Self-Challenging Language Model Agents
1020. NeurIPS 2025Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks
1021. NeurIPS 2025Self-Guided Hierarchical Exploration for Generalist Foundation Model Web Agents
1022. NeurIPS 2025Sequential Multi-Agent Dynamic Algorithm Configuration
1023. NeurIPS 2025ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling
1024. NeurIPS 2025Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents
1025. NeurIPS 2025Simulating Society Requires Simulating Thought
1026. NeurIPS 2025Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models
1027. NeurIPS 2025SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds
1028. NeurIPS 2025SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
1029. NeurIPS 2025SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific Sketches
1030. NeurIPS 2025Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation is Wasteful
1031. NeurIPS 2025SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
1032. NeurIPS 2025SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions
1033. NeurIPS 2025SpecEM: Training-Free LLM Ensembling via Iterative Drafting, Verification, and Online Feedback
1034. NeurIPS 2025SpecMAS: A Multi-Agent System for Self-Verifying System Generation via Formal Model Checking
1035. NeurIPS 2025SSRB: Direct Natural Language Querying to Massive Heterogeneous Semi-Structured Data
1036. NeurIPS 2025Stabilizing LTI Systems under Partial Observability: Sample Complexity and Fundamental Limits
1037. NeurIPS 2025Stackelberg Learning with Outcome-based Payment
1038. NeurIPS 2025STEER-ME: Assessing the Microeconomic Reasoning of Large Language Models
1039. NeurIPS 2025STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Clouds
1040. NeurIPS 2025Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs
1041. NeurIPS 2025SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications
1042. NeurIPS 2025SWE-bench Goes Live!
1043. NeurIPS 2025SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
1044. NeurIPS 2025SWE-smith: Scaling Data for Software Engineering Agents
1045. NeurIPS 2025SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset
1046. NeurIPS 2025SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assembly
1047. NeurIPS 2025Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning
1048. NeurIPS 2025Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration
1049. NeurIPS 2025T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning
1050. NeurIPS 2025TAI3: Testing Agent Integrity in Interpreting User Intent

FAQ

How many AI Agents papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

3,266 in total: 170 in 2023, 329 in 2024, 784 in 2025, 1,983 in 2026.

How many AI Agents papers are at NeurIPS 2026?

NeurIPS 2026 has 729 AI Agents papers, versus 362 the year before.

How many AI Agents papers are at ICLR 2026?

ICLR 2026 has 500 AI Agents papers, versus 204 the year before.

How many AI Agents papers are at ICML 2026?

ICML 2026 has 640 AI Agents papers, versus 178 the year before.

How many AI Agents papers are at CVPR 2026?

CVPR 2026 has 114 AI Agents papers, versus 40 the year before.

Which conference publishes the most AI Agents papers?

NeurIPS, with 1,317 papers from 2023 to 2026.