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 11 of 27

501. NeurIPS 2026PurpleAudit: A Co-Evolutionary Auditing Framework for Task Hijacking in Multi-Agent Systems
502. NeurIPS 2026Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing
503. NeurIPS 2026QUEST: Q-Learning for Uncertainty-Guided Efficient Search Teams
504. NeurIPS 2026RA$^2$: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning
505. NeurIPS 2026RADAR: Routing Agents via Difficulty-Aware Recovery
506. NeurIPS 2026RAG in a Trenchcoat: When Minimal Memory Is Enough for Agentic Systems, and When It Isn’t
507. NeurIPS 2026RAOP: Step-Level Resource Orchestration for LLM Agents across Edge and Cloud
508. NeurIPS 2026Rare Disease Diagnosis Agent with Decoupled Workflows and Knowledge-Driven Self-Evaluation
509. NeurIPS 2026ReCoVer: Resilient LLM Pre-Training System via Fault-Tolerant Collective and Versatile Workload
510. NeurIPS 2026Recovering the Apresjan Hierarchy Using Linkage-Based Clustering
511. NeurIPS 2026Recursive Multi-Agent Systems
512. NeurIPS 2026ReGen: Agentic Video World Modeling with Synergized Reasoning and Generation
513. NeurIPS 2026REINS: A Self-Evolving Agent Harness for Real-Time Trajectory Planning
514. NeurIPS 2026RelAgent: LLM Agents as Data Scientists for Relational Learning
515. NeurIPS 2026Relevance Is Not Necessity: Selecting the Necessary API Set for Tool-Using LLMs
516. NeurIPS 2026Replicas-as-Variables: A Planner for Throughput-Optimal Routing in LLM Deployment
517. NeurIPS 2026RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
518. NeurIPS 2026RepoZero: Can LLMs Generate a Code Repository from Scratch?
519. NeurIPS 2026Resilience Matters for Embodied Agents System: New Metrics, Systematic Evaluation, and Optimization
520. NeurIPS 2026Rethinking Bayesian Optimization for Co-Optimizing LLM Training Configurations
521. NeurIPS 2026Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
522. NeurIPS 2026Rethinking in Spikes: Mitigating Hallucinations in MDLMs with Step-Aware Decoding
523. NeurIPS 2026Rethinking Latency Denial-of-Service: Attack the LLM Serving Framework, Not the Model
524. NeurIPS 2026Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning
525. NeurIPS 2026REVERSE: Reinforcing Evidence Verification and Search for Agentic Image Geolocation
526. NeurIPS 2026Reward Modeling for Multi-Agent Orchestration
527. NeurIPS 2026RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with LLMs
528. NeurIPS 2026RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents
529. NeurIPS 2026RIGOR: Risk-Gated Topology Adaptation for Robust LLM Multi-Agent Reasoning
530. NeurIPS 2026Risk-Calibrated Context Selection for Healthcare Multi-Agent Handoff
531. NeurIPS 2026RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agents
532. NeurIPS 2026RL-Guided Temporal Localization for Dual-Channel Retrieval in Long-Horizon Agent Memory
533. NeurIPS 2026RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades
534. NeurIPS 2026RoboWits: Unexpected Challenges for Robotic Creative Problem Solving
535. NeurIPS 2026Routeability Before Routing: Routeability Audit Protocol (RAP) and RouteabilityBench for Audited LLM Model Selection
536. NeurIPS 2026RTEB: An Overfitting-Resistant Benchmark for Embedding Model Evaluation
537. NeurIPS 2026RuleSmith: Multi-Agent LLMs for Automated Game Balancing
538. NeurIPS 2026Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic
539. NeurIPS 2026RVR: Retrieve-Verify-Retrieve for Comprehensive Question Answering
540. NeurIPS 2026S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields
541. NeurIPS 2026SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?
542. NeurIPS 2026SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering
543. NeurIPS 2026Safe Actions Can Form Unsafe Traces: Benchmarking and Shielding Compositional Emergent Risk in AI Agents
544. NeurIPS 2026Safe-Fair MACPO: Burden-Fair Constrained Policy Optimization for Safe Multi-Agent Reinforcement Learning
545. NeurIPS 2026Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents
546. NeurIPS 2026SageSched: Efficient LLM Scheduling Confronting Demand Uncertainty and Hybridity
547. NeurIPS 2026Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents
548. NeurIPS 2026Sandboxed Coding Agents are Competitive Omni-modal Task Solvers
549. NeurIPS 2026Scalable Minimal-Change Learning for Controllable Image Editing
550. NeurIPS 2026Scalable Multi-Agent Contrastive Reinforcement Learning

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.