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 12 of 27

551. NeurIPS 2026SceneFactory: GPU-Accelerated Multi-Agent Driving Simulation with Physics-Based Vehicle Dynamics
552. NeurIPS 2026SchemeArena: Factorized Stress Testing of Scheming in LLM Agents
553. NeurIPS 2026SCHOLARPEER: A Multi-Agent Framework for Automated Peer Review
554. NeurIPS 2026SciResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery
555. NeurIPS 2026ScrapeBench: Evaluating Legal Compliance of AI Agents in Website Scraping
556. NeurIPS 2026scShapeBench: Discovering geometry from high dimensional scRNAseq data
557. NeurIPS 2026SeaPilot: Mobile Agent with Self-refining Environment Alignment
558. NeurIPS 2026SecureClaw: Clawing Back Control of LLM Agents
559. NeurIPS 2026Securing AI Agents with Information-Flow Control
560. NeurIPS 2026Seeing Beyond the Next Step: World-Model-Guided Human-Like Navigation in Multi-Agent Scenes
561. NeurIPS 2026SEEK-VAU: Towards Evidence-Faithful Video Anomaly Understanding via Agentic Search
562. NeurIPS 2026Selective Answering for Medical VQA via Parallel Independent Claim Verification
563. NeurIPS 2026Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL
564. NeurIPS 2026Self-Compacting Language Model Agents
565. NeurIPS 2026Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback
566. NeurIPS 2026Self-Evolving Agents Should Build Internal and External Models of the World
567. NeurIPS 2026Self-Programmed Execution for Language-Model Agents
568. NeurIPS 2026Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration
569. NeurIPS 2026Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation
570. NeurIPS 2026Sequential Behavioral Watermarking for LLM Agents
571. NeurIPS 2026Sharpness, Stability, and Step-Size Scaling in Deep Polynomial Networks
572. NeurIPS 2026Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace
573. NeurIPS 2026SIGA: Scientific Simulation Coding Agent Adapter- A Geophysics Case Study
574. NeurIPS 2026SiliconBench: Speed, Memory, and Fidelity for LLM Inference on Apple Silicon
575. NeurIPS 2026Simple Baselines are Competitive with Code Evolution
576. NeurIPS 2026Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
577. NeurIPS 2026Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
578. NeurIPS 2026SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
579. NeurIPS 2026SkillMaster: Toward Autonomous Skill Mastery in LLM Agents
580. NeurIPS 2026SkillOpt: Executive Strategy for Self-Evolving Agent Skills
581. NeurIPS 2026SkillOrchestra: Learning to Route Agents via Skill Transfer
582. NeurIPS 2026SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
583. NeurIPS 2026SKIM: Pruning Large Language Model Agents via Selective Knowledge Informed Masking
584. NeurIPS 2026Slide P2V-Bench: A Cross-Domain Benchmark for Slide-Centric Scientific Paper-to-Presentation Video Generation
585. NeurIPS 2026SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
586. NeurIPS 2026SMART: Scalable Multi-Agent Role-conditioned Teaming via LLM-free Tree Search
587. NeurIPS 2026Social Interaction Breaks Replicate Independence in Controlled-Clone LLM Agents
588. NeurIPS 2026SoDeArena: A Socially-Situated Reasoning Benchmark for Large Language Models
589. NeurIPS 2026SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits
590. NeurIPS 2026SOLAR: AI-Powered Speed-of-Light Performance Analysis
591. NeurIPS 2026Solaris: Building a Multiplayer Video World Model in Minecraft
592. NeurIPS 2026Solving Every Step Is Not Enough: Milestone Oracles Reveal a Composition Gap in LLM Math Reasoning
593. NeurIPS 2026Soteria: Formally Verified Planning with Runtime Enforcement for Safe LLM Agents
594. NeurIPS 2026SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference
595. NeurIPS 2026SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
596. NeurIPS 2026SpecForge: Agent-Oriented Code Documentation Optimization via Multi-Frontier Tree Search
597. NeurIPS 2026Specialists Hold, Generalists Discount: Asymmetric Equilibrium in LLM Routing Auctions
598. NeurIPS 2026Spend Only What You Need: Defect-Aware Residual Coverage for Efficient Multi-Agent Reasoning
599. NeurIPS 2026SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving
600. NeurIPS 2026SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows

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.