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 22 of 27

1051. NeurIPS 2025Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
1052. NeurIPS 2025The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements
1053. NeurIPS 2025The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement
1054. NeurIPS 2025TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
1055. NeurIPS 2025Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
1056. NeurIPS 2025Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time Interaction
1057. NeurIPS 2025Thought Communication in Multiagent Collaboration
1058. NeurIPS 2025Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
1059. NeurIPS 2025Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking
1060. NeurIPS 2025TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop
1061. NeurIPS 2025ToolRL: Reward is All Tool Learning Needs
1062. NeurIPS 2025Towards Doctor-Like Reasoning: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients
1063. NeurIPS 2025Towards Principled Unsupervised Multi-Agent Reinforcement Learning
1064. NeurIPS 2025TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration
1065. NeurIPS 2025Transcending Cost-Quality Tradeoff in Agent Serving via Session-Awareness
1066. NeurIPS 2025Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning
1067. NeurIPS 2025TRAP: Targeted Redirecting of Agentic Preferences
1068. NeurIPS 2025Tri-MARF: A Tri-Modal Multi-Agent Responsive Framework for Comprehensive 3D Object Annotation
1069. NeurIPS 2025TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets
1070. NeurIPS 2025UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents
1071. NeurIPS 2025UniMotion: A Unified Motion Framework for Simulation, Prediction and Planning
1072. NeurIPS 2025URB - Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles
1073. NeurIPS 2025UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception
1074. NeurIPS 2025Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
1075. NeurIPS 2025VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
1076. NeurIPS 2025VideoCAD: A Dataset and Model for Learning Long‑Horizon 3D CAD UI Interactions from Video
1077. NeurIPS 2025VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
1078. NeurIPS 2025VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture
1079. NeurIPS 2025VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play
1080. NeurIPS 2025WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
1081. NeurIPS 2025WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
1082. NeurIPS 2025Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
1083. NeurIPS 2025WebDancer: Towards Autonomous Information Seeking Agency
1084. NeurIPS 2025WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch
1085. NeurIPS 2025What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions
1086. NeurIPS 2025Who You Are Matters: Bridging Interests and Social Roles via LLM-Enhanced Logic Recommendation
1087. NeurIPS 2025Why Do Multi-Agent LLM Systems Fail?
1088. NeurIPS 2025Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints
1089. NeurIPS 2025Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs
1090. NeurIPS 2025Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration
1091. NeurIPS 2025Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding
1092. NeurIPS 2024A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health
1093. NeurIPS 2024A Synthetic Dataset for Personal Attribute Inference
1094. NeurIPS 2024AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making
1095. NeurIPS 2024Agent Planning with World Knowledge Model
1096. NeurIPS 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
1097. NeurIPS 2024AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
1098. NeurIPS 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
1099. NeurIPS 2024AGILE: A Novel Reinforcement Learning Framework of LLM Agents
1100. NeurIPS 2024ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation

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.