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 15 of 27

701. NeurIPS 2026Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games
702. NeurIPS 2026What Claims Do LLM Benchmark Scores Support?
703. NeurIPS 2026What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents
704. NeurIPS 2026What Makes Two States the Same? Value-Aware State Matching for Multi-Turn Agent Credit Assignment
705. NeurIPS 2026What Should Remain After Forgetting? Rethinking LLM Unlearning as Predictive Posterior Correction
706. NeurIPS 2026What Stops SGD on LLM Pre-Training: The Need for Large Learning Rate and How to Achieve it
707. NeurIPS 2026When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?
708. NeurIPS 2026When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning
709. NeurIPS 2026When Do Multi-Agent Systems Help? An Information Bottleneck Perspective
710. NeurIPS 2026When Expert Disagreement Hurts: Auditing Prestige-Sensitive Revision in LLM Decision Pipelines
711. NeurIPS 2026When Further Realization Is Unnecessary: Amortized Reasoning for Long-Horizon LLM Agents
712. NeurIPS 2026When LLM Routers Overpay: Strong-Model Over-Selection under Loose Budgets
713. NeurIPS 2026When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding
714. NeurIPS 2026When the Most Disruptive Messages Are Safe to Prune in Aggregate: Functional Analysis of Communication Pruning in Two-Agent LLM Systems
715. NeurIPS 2026Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers
716. NeurIPS 2026Who Should Evolve? Uncertainty-Aware Role Bottleneck Inference for Multi-Agent LLM Training
717. NeurIPS 2026Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?
718. NeurIPS 2026Why Copy Others? Insights into Social Learning from Multi-Agent Reinforcement Learning
719. NeurIPS 2026WiREBench: Evaluating AI Agents' Capabilities in Reverse-Engineering Black-Box Applications in the Real World
720. NeurIPS 2026Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies
721. NeurIPS 2026World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning
722. NeurIPS 2026WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction
723. NeurIPS 2026WURI: Watching Unfolding Risk in Agent Interactions
724. NeurIPS 2026XBRIDGE: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication
725. NeurIPS 2026XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity
726. NeurIPS 2026Youdunit: Single-Call Counterfactual Necessity in Multi-Agent LLM Systems
727. NeurIPS 2026ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration
728. NeurIPS 2026Zero-Shot Coordination among LLM Agents
729. NeurIPS 2026Zero-Violation Regret for Cooperative Markov Games with Coupled Instantaneous Hard Constraints
730. NeurIPS 20253DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
731. NeurIPS 20254KAgent: Agentic Any Image to 4K Super-Resolution
732. NeurIPS 2025A machine learning approach that beats Rubik's cubes
733. NeurIPS 2025A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond
734. NeurIPS 2025A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
735. NeurIPS 2025A-Mem: Agentic Memory for LLM Agents
736. NeurIPS 2025Abstract Counterfactuals for Language Model Agents
737. NeurIPS 2025AC-LoRA: (Almost) Training-Free Access Control Aware Multi-Modal LLMs
738. NeurIPS 2025Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning
739. NeurIPS 2025Adaptive Preference Arithmetic: A Personalized Agent with Adaptive Preference Arithmetic for Dynamic Preference Modeling
740. NeurIPS 2025Adaptively Coordinating with Novel Partners via Learned Latent Strategies
741. NeurIPS 2025AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios
742. NeurIPS 2025AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents
743. NeurIPS 2025AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement
744. NeurIPS 2025AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
745. NeurIPS 2025Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents
746. NeurIPS 2025Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem Solving
747. NeurIPS 2025AGENTIF: Benchmarking Large Language Models Instruction Following Ability in Agentic Scenarios
748. NeurIPS 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
749. NeurIPS 2025AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
750. NeurIPS 2025Agents Robust to Distribution Shifts Learn Causal World Models Even Under Mediation

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.