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

3,266 papers, page 21 of 66

1001. ICML 2026Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
1002. ICML 2026Navigating the Energy Landscape of Collaboration: Multi-Agent Communication Graph Generation via Score-Based Diffusion
1003. ICML 2026NEMO: Execution-Aware Optimization Modeling via Autonomous Coding Agents
1004. ICML 2026Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense
1005. ICML 2026NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents
1006. ICML 2026NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search
1007. ICML 2026Not All Prefills Are Equal: PPD Disaggregation for Multi-turn LLM Serving
1008. ICML 2026Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics
1009. ICML 2026Off-Policy Evaluation with Strategic Agents via Local Disclosure
1010. ICML 2026Offline Multi-agent Continual Cooperation via Skill Partition and Reuse
1011. ICML 2026Offline Multi-Agent Reinforcement Learning via Sequential Score Decomposition
1012. ICML 2026OLion: Approaching the Hadamard Ideal by Intersecting Spectral and L inf Implicit Biases
1013. ICML 2026OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration
1014. ICML 2026On Effectiveness and Efficiency of Agentic Tool-calling and RL Training
1015. ICML 2026On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement
1016. ICML 2026On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents
1017. ICML 2026On Path to Multimodal Historical Reasoning: HistBench and HistAgent
1018. ICML 2026On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length
1019. ICML 2026One Tool Is Enough: Reinforcement Learning of LLM Agents for Repository-Level Code Navigation
1020. ICML 2026One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining
1021. ICML 2026Online Linear Programming for Multi-Objective Routing in LLM Serving
1022. ICML 2026OpenDeception: Learning Deception and Trust in Human–AI Interaction via Multi-Agent Simulation
1023. ICML 2026OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft
1024. ICML 2026OpenSage: Self-programming Agent Generation Engine
1025. ICML 2026Ophiuchus: Incentivizing Tool-augmented ''Think with Images'' for Joint Medical Segmentation, Understanding and Reasoning
1026. ICML 2026Opt-Miner: Empowering Information-Seeking Agent with Tree-Guided Data Synthesis for Optimization Modeling
1027. ICML 2026Optimal and Scalable MAPF via Multi-Marginal Optimal Transport and Schrödinger Bridges
1028. ICML 2026Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers
1029. ICML 2026Optimal Rates for Feasible Payoff Set Estimation in Games
1030. ICML 2026Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward
1031. ICML 2026OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing
1032. ICML 2026OServe: Accelerating LLM Serving via Spatial-Temporal Workload Orchestration
1033. ICML 2026OSM+: Billion-Level Open Street Map Dataset for City-wide Experiments
1034. ICML 2026OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
1035. ICML 2026Outrunning LLM Cutoffs: A Live Kernel Crash Resolution Benchmark for All
1036. ICML 2026PaperBanana: Automating Academic Illustration for AI Scientists
1037. ICML 2026ParamMem: Augmenting Language Agents with Parametric Reflective Memory
1038. ICML 2026ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution
1039. ICML 2026PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs
1040. ICML 2026PDAgent: An LLM-Driven Autonomous Agent Framework Towards *In Silico* Protein Design via Directed Mutation
1041. ICML 2026Persistent Semantic Entities in Tool-Augmented LLM Systems
1042. ICML 2026Persona-Pruner: Sculpting Lightweight Models for Role-Playing
1043. ICML 2026Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History
1044. ICML 2026Pessimistic Verification for Open-Ended Math Questions
1045. ICML 2026PGS: Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback
1046. ICML 2026Phase-Aware Mixture of Experts for Agentic Reinforcement Learning
1047. ICML 2026PinTok: Tokenizers Deserve Dedicated Pinned CPU-Compute and Memory
1048. ICML 2026Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control
1049. ICML 2026PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
1050. ICML 2026POLCA: Stochastic Generative Optimization with LLM

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.