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 14 of 27

651. NeurIPS 2026TimeWarp: Evaluating Web Agents by Revisiting the Past
652. NeurIPS 2026To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
653. NeurIPS 2026TokenRouter: Efficient Serving System for Token-Level LLM Routing
654. NeurIPS 2026ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
655. NeurIPS 2026Tools as Continuous Flow for Evolving Agentic Reasoning
656. NeurIPS 2026ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning
657. NeurIPS 2026TopoScope: A Graph-Scoped LLM Agent for Printed Circuit Board Schematic Design
658. NeurIPS 2026Toward Interactive Understanding of Code APIs
659. NeurIPS 2026Toward Online Robust Zero-Sum Markov Games with Function Approximation
660. NeurIPS 2026Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows
661. NeurIPS 2026Towards Effective and Transferable Physical Camouflage against Multi-View BEV-based 3D Perception in Autonomous Driving
662. NeurIPS 2026Towards High Semantic Fidelity: Hyperdimensional Symbolic Messages in Multi-Agent Communication
663. NeurIPS 2026Towards Realistic Conversational Multimodal Instruction Following
664. NeurIPS 2026Towards Reliable LLM Evaluation: Correcting the Winner’s Curse in Adaptive Benchmarking
665. NeurIPS 2026Towards Unified Memory Adaptation for LLM Agents: Textual, Latent, and Parametric Pathways
666. NeurIPS 2026TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development
667. NeurIPS 2026Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations
668. NeurIPS 2026Training Agent to Scale Inference-Time Reasoning
669. NeurIPS 2026Training Generalizable Collaborative Agents via Strategic Risk Aversion
670. NeurIPS 2026Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
671. NeurIPS 2026Training on Documents About Monitoring Leads to CoT Obfuscation
672. NeurIPS 2026TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents
673. NeurIPS 2026Treat Domain-Specific Languages as Design Variables in LLM Agents
674. NeurIPS 2026Tree Training: Efficient LLM Training on Tree-Structured Trajectories
675. NeurIPS 2026TrialAgentBench: Evaluating AI Agents for Clinical-Trial Analysis and Long-Horizon Drug-Development Decisions
676. NeurIPS 2026TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks
677. NeurIPS 2026Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning
678. NeurIPS 2026Trust, but Don’t Verify: Epistemic Blind Spots in LLM Source Evaluation
679. NeurIPS 2026TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning
680. NeurIPS 2026TwinFlux: One-Step Discrete-Continuous Flow for End-to-End Autonomous Driving
681. NeurIPS 2026TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
682. NeurIPS 2026Two is better than one: designing heterogeneous scales in binary rating systems
683. NeurIPS 2026UMAS: System-Level Uncertainty Quantification for Multi-Agent LLM Systems
684. NeurIPS 2026UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image
685. NeurIPS 2026UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
686. NeurIPS 2026Unified Resource-Grounded Coordination Protocol for Orchestrator-Free Heterogeneous Multi-Agent Systems
687. NeurIPS 2026Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis
688. NeurIPS 2026Untrusted Content Masking for Web Agents with Security Guarantees
689. NeurIPS 2026Useful Memories Become Faulty When Continuously Updated by LLMs
690. NeurIPS 2026Veri-Sure: Multi-Agent RTL Code Generation with Temporal Tracing, Slicing and Formal Verification
691. NeurIPS 2026VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
692. NeurIPS 2026VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora
693. NeurIPS 2026VeruSAGE-Bench: A Benchmark Suite for Rust System Verification
694. NeurIPS 2026VESTA: Visual Exploration with Statistical Tool Agents
695. NeurIPS 2026VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation
696. NeurIPS 2026VideoSleuth: A Narrative-Centric Agentic System with Video-Audio Native MLLM for Long-Form Video Understanding
697. NeurIPS 2026Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
698. NeurIPS 2026VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic Model
699. NeurIPS 2026Visual Harness: Grounding Multimodal Reasoning in Physics Engines
700. NeurIPS 2026Vortex: Efficient and Programmable Sparse Attention Serving

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.