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

640 papers, page 9 of 13

401. ICML 2026On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement
402. ICML 2026On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents
403. ICML 2026On Path to Multimodal Historical Reasoning: HistBench and HistAgent
404. ICML 2026On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length
405. ICML 2026One Tool Is Enough: Reinforcement Learning of LLM Agents for Repository-Level Code Navigation
406. ICML 2026One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining
407. ICML 2026Online Linear Programming for Multi-Objective Routing in LLM Serving
408. ICML 2026OpenDeception: Learning Deception and Trust in Human–AI Interaction via Multi-Agent Simulation
409. ICML 2026OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft
410. ICML 2026OpenSage: Self-programming Agent Generation Engine
411. ICML 2026Ophiuchus: Incentivizing Tool-augmented ''Think with Images'' for Joint Medical Segmentation, Understanding and Reasoning
412. ICML 2026Opt-Miner: Empowering Information-Seeking Agent with Tree-Guided Data Synthesis for Optimization Modeling
413. ICML 2026Optimal and Scalable MAPF via Multi-Marginal Optimal Transport and Schrödinger Bridges
414. ICML 2026Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers
415. ICML 2026Optimal Rates for Feasible Payoff Set Estimation in Games
416. ICML 2026Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward
417. ICML 2026OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing
418. ICML 2026OServe: Accelerating LLM Serving via Spatial-Temporal Workload Orchestration
419. ICML 2026OSM+: Billion-Level Open Street Map Dataset for City-wide Experiments
420. ICML 2026OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
421. ICML 2026Outrunning LLM Cutoffs: A Live Kernel Crash Resolution Benchmark for All
422. ICML 2026PaperBanana: Automating Academic Illustration for AI Scientists
423. ICML 2026ParamMem: Augmenting Language Agents with Parametric Reflective Memory
424. ICML 2026ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution
425. ICML 2026PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs
426. ICML 2026PDAgent: An LLM-Driven Autonomous Agent Framework Towards *In Silico* Protein Design via Directed Mutation
427. ICML 2026Persistent Semantic Entities in Tool-Augmented LLM Systems
428. ICML 2026Persona-Pruner: Sculpting Lightweight Models for Role-Playing
429. ICML 2026Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History
430. ICML 2026Pessimistic Verification for Open-Ended Math Questions
431. ICML 2026PGS: Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback
432. ICML 2026Phase-Aware Mixture of Experts for Agentic Reinforcement Learning
433. ICML 2026PinTok: Tokenizers Deserve Dedicated Pinned CPU-Compute and Memory
434. ICML 2026Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control
435. ICML 2026PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
436. ICML 2026POLCA: Stochastic Generative Optimization with LLM
437. ICML 2026Policies Permitting LLM Use for Polishing Peer Reviews Are Currently Not Enforceable
438. ICML 2026Policy-Driven World Model Adaptation for Robust Offline Model-based Reinforcement Learning
439. ICML 2026Post-Training LLMs as Better Decision-Making Agents: A Regret-Minimization Approach
440. ICML 2026PosterAgent: Agentic Poster Generation via Stage-Aware Reinforcement Learning
441. ICML 2026PostTrainBench: Can LLM Agents Automate LLM Post-Training?
442. ICML 2026PPT-Eval: A Benchmark for Computer-Use Agents on PowerPoint Tasks
443. ICML 2026PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training
444. ICML 2026PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
445. ICML 2026Prefix-Cache-Aware Data Reordering for LLM-Augmented Database Analytics
446. ICML 2026Principle-Evolvable Scientific Discovery via Uncertainty Minimization
447. ICML 2026PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Training
448. ICML 2026PrivGate: Steering Contextual Integrity in LLMs via Latent Space Geometry
449. ICML 2026Privileged Information Distillation for Language Models
450. ICML 2026ProAct: A Benchmark and Multimodal Framework for Structure-Aware Proactive Response

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.