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

3,266 papers, page 10 of 66

451. ICLR 2026Pursuing Minimal Sufficiency in Spatial Reasoning
452. ICLR 2026Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification
453. ICLR 2026QLCoder: A Query Synthesizer For Static Analysis of Security Vulnerabilities
454. ICLR 2026Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models
455. ICLR 2026R-WoM: Retrieval-augmented World Model For Computer-use Agents
456. ICLR 2026Randomization Boosts KV Caching, Learning Balances Query Load: A Joint Perspective
457. ICLR 2026RATE-DISTORTION OPTIMIZED COMMUNICATION FOR COLLABORATIVE PERCEPTION
458. ICLR 2026Rating Quality of Diverse Time Series Data by Meta-learning from LLM Judgment
459. ICLR 2026Real-Time Reasoning Agents in Evolving Environments
460. ICLR 2026ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
461. ICLR 2026ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures
462. ICLR 2026RECODE: A Benchmark for Research Code DEvelopment with Interactive Human Feedback
463. ICLR 2026RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents
464. ICLR 2026RedSage: A Cybersecurity Generalist LLM
465. ICLR 2026RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
466. ICLR 2026Reducing Belief Deviation in Reinforcement Learning for Active Reasoning
467. ICLR 2026REI-Bench: Can Embodied Agents Understand Vague Human Instructions in Task Planning?
468. ICLR 2026ReIn: Conversational Error Recovery with Reasoning Inception
469. ICLR 2026Reinforcement Learning for Machine Learning Engineering Agents
470. ICLR 2026Reliable Weak-to-Strong Monitoring of LLM Agents
471. ICLR 2026REMem: Reasoning with Episodic Memory in Language Agent
472. ICLR 2026Repurposing Synthetic Data for Fine-grained Search Agent Supervision
473. ICLR 2026ResearchRubrics: A Benchmark of Prompts and Rubrics For Deep Research Agents
474. ICLR 2026Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosis
475. ICLR 2026Retaining Suboptimal Actions to Follow Shifting Optima in Multi-Agent Reinforcement Learning
476. ICLR 2026Rethinking Residual Errors in Compensation-based LLM Quantization
477. ICLR 2026ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
478. ICLR 2026Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval
479. ICLR 2026ReVeal: Self-Evolving Code Agents via Reliable Self-Verification
480. ICLR 2026Revisiting Parameter Server in LLM Post-Training
481. ICLR 2026ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesis
482. ICLR 2026RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy
483. ICLR 2026Risk-Sensitive Agent Compositions
484. ICLR 2026RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents
485. ICLR 2026RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents
486. ICLR 2026Robust LLM Unlearning via Post Judgment and Multi-round Thinking
487. ICLR 2026ROGA: Scaling Generalist Agents for Office Productivity Tasks via Tool Generation
488. ICLR 2026RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
489. ICLR 2026Safe Continuous-time Multi-Agent Reinforcement Learning via Epigraph Form
490. ICLR 2026Sample-Efficient Distributionally Robust Multi-Agent Reinforcement Learning via Online Interaction
491. ICLR 2026Scalable Oversight via Partitioned Human Supervision
492. ICLR 2026ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data
493. ICLR 2026Scaling Agent Learning via Experience Synthesis
494. ICLR 2026Scaling Agents via Continual Pre-training
495. ICLR 2026Scaling Generalist Data-Analytic Agents
496. ICLR 2026Scaling Synthetic Task Generation for Agents via Exploration
497. ICLR 2026Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation
498. ICLR 2026ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows
499. ICLR 2026SciNav: A Principled Agent Framework for Scientific Coding Tasks
500. ICLR 2026SCUBA: Salesforce Computer Use Benchmark

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.