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 10 of 27

451. NeurIPS 2026Open-Ended Scientific Discovery and the Social Dynamics of Evolving Agent Networks
452. NeurIPS 2026OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
453. NeurIPS 2026OpenSearcher: Democratizing Deep Search through a Fully Offline Pipeline with Programmatic Verification
454. NeurIPS 2026Optimal Contextual Pricing under Agnostic Non-Lipschitz Demand
455. NeurIPS 2026Optimize Once, Execute Fast: Latency-Aware Multi-Agent Workflow Learning for Recurrent Queries
456. NeurIPS 2026Optimizing Agent Tool-Use via Trajectory-based Insight Evolution
457. NeurIPS 2026Optimizing Analytic Constants via AI-Guided Lean Proof Refinement
458. NeurIPS 2026OrchestraRL: Learning to Orchestrate LLM Agent Swarms with Entropy-Aware Communication Control
459. NeurIPS 2026OS-Omni: A Cross-Platform Benchmark for Generalist Computer-Using Agents
460. NeurIPS 2026Overcoming Attention Distraction: Training-Free Latent Communication for Multi-Agent Systems
461. NeurIPS 2026Overthinking as a Symptom of Knowledge Conflict: Understanding and Detecting LLM's Hallucinations in Retrieval-Augmented Question Answering
462. NeurIPS 2026P$^{3}$: Joint Program-and-Proof Planning\\ for Verified Code Generation
463. NeurIPS 2026Pacing Branch Parallelism in LLM Serving
464. NeurIPS 2026PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
465. NeurIPS 2026ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
466. NeurIPS 2026PatchScout: Thematic Web Data Collection via Information Foraging
467. NeurIPS 2026PatternBloom: Empowering Agentic RAG with Externalized RL-Distilled Graph Patterns
468. NeurIPS 2026PBT-Bench: Benchmarking AI Agents on Property-Based Testing
469. NeurIPS 2026PCBInnoBench: Benchmarking LLM Agents on Real-World PCB Design
470. NeurIPS 2026PCFBench: How Far Can Large Vision-Language Models Go in Physics-aware Photonic Inverse Design?
471. NeurIPS 2026PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents
472. NeurIPS 2026Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-Horizon Agents
473. NeurIPS 2026PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning
474. NeurIPS 2026PhysAgentGym: Free Physical-Law Verifiers for Training Small Code-Reasoning Agents
475. NeurIPS 2026PiCA: Pivot-Based Credit Assignment For Search Agentic Reinforcement Learning
476. NeurIPS 2026PieArena: Ranking and Profiling Language Agents in Realistic Negotiation Scenarios
477. NeurIPS 2026PithTrain: A Compact and Agent-Native MoE Training System
478. NeurIPS 2026PIVOT: A Unified Agentic Framework for Streaming Long-Video Understanding
479. NeurIPS 2026PLATO: Pointer Learner for Agent and Task Openness
480. NeurIPS 2026Playing Markov Games Without Observing Payoffs
481. NeurIPS 2026Policy-Level Exploration for Coordinated Multi-Agent Reinforcement Learning
482. NeurIPS 2026Population-Aligned Persona Generation for LLM-based Social Simulation
483. NeurIPS 2026Position: A Safe LLM and a Safe Harness Do Not Make a Safe Agent
484. NeurIPS 2026Position: Machine Learning Conferences Should Introduce an Autonomous Research Track
485. NeurIPS 2026Posterior Sampling-based Online Learning for Episodic POMDPs
486. NeurIPS 2026Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning
487. NeurIPS 2026Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?
488. NeurIPS 2026PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents
489. NeurIPS 2026Predicting What Changes: Causal Delta World Models for Risk-Aware LLM Agent Planning
490. NeurIPS 2026Prefix Executability: Evaluating Tool-Using Agents Beyond Final Success
491. NeurIPS 2026Preventing Error Cascades in Long-Horizon Multimodal Agents with Edge-Reliability Graph Memory
492. NeurIPS 2026Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design
493. NeurIPS 2026PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents
494. NeurIPS 2026ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts
495. NeurIPS 2026Profit Maximization in Bilateral Trade against a Smooth Adversary
496. NeurIPS 2026ProGraf: Profile-Guided Planning for Step-by-Step Generation of Structured Non-Natural Images
497. NeurIPS 2026ProgramBench: Can Language Models Rebuild Programs From Scratch?
498. NeurIPS 2026Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents
499. NeurIPS 2026Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble
500. NeurIPS 2026Proper Scoring Rules for Agentic Uncertainty Quantification

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.