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

500 papers, page 10 of 10

451. ICLR 2026Towards Self-Evolving Agent Benchmarks : Validatable Agent Trajectory via Test-Time Exploration
452. ICLR 2026Towards Sustainable Investment Policies Informed by Opponent Shaping
453. ICLR 2026Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading
454. ICLR 2026TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use
455. ICLR 2026Tree Search for LLM Agent Reinforcement Learning
456. ICLR 2026Trinity: An Evolved LLM Coordinator
457. ICLR 2026Triple-BERT: Do We Really Need MARL for Order Dispatch on Ride-Sharing Platforms?
458. ICLR 2026TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them
459. ICLR 2026TS$^2$: Training with Sparsemax+, Testing with Softmax for Accurate and Diverse LLM Fine-Tuning
460. ICLR 2026TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture
461. ICLR 2026TusoAI: Agentic Optimization for Scientific Methods
462. ICLR 2026UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction as Reasoning
463. ICLR 2026UIS-Digger: Towards Comprehensive Research Agent Systems for Real-world Unindexed Information Seeking
464. ICLR 2026Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
465. ICLR 2026Unlocking Full Efficiency of Token Filtering in Large Language Model Training
466. ICLR 2026Unlocking Long-Horizon Agentic Search with Large-Scale End-to-End RL
467. ICLR 2026Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation
468. ICLR 2026Unveiling the Potential of Diffusion Large Language Model in Controllable Generation
469. ICLR 2026USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning Capabilities of LLMs as Urban Agents
470. ICLR 2026VeriEquivBench: An Equivalence Score for Ground-Truth-Free Evaluation of Formally Verifiable Code
471. ICLR 2026VeriRole: Verifiable Role-Awareness through Hint-Guided Reinforcement Learning
472. ICLR 2026VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning
473. ICLR 2026VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning
474. ICLR 2026Virtual Community: An Open World for Humans, Robots, and Society
475. ICLR 2026VisCoder2: Building Multi-Language Visualization Coding Agents
476. ICLR 2026Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow
477. ICLR 2026VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications
478. ICLR 2026VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
479. ICLR 2026WALT: Web Agents that Learn Tools
480. ICLR 2026Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents
481. ICLR 2026WebArbiter: A Generative Reasoning Process Reward Model for Web Agents
482. ICLR 2026WebDevJudge: Evaluating (M)LLMs as Critiques for Web Development Quality
483. ICLR 2026WebDS: An End-to-End Benchmark for Web-based Data Science
484. ICLR 2026WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents
485. ICLR 2026WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning
486. ICLR 2026WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning
487. ICLR 2026WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection
488. ICLR 2026WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization
489. ICLR 2026WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research
490. ICLR 2026When Agents “Misremember” Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems
491. ICLR 2026When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework
492. ICLR 2026When Is Diversity Rewarded in Cooperative Multi-Agent Learning?
493. ICLR 2026When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling
494. ICLR 2026Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing
495. ICLR 2026Who Matters Matters: Agent-Specific Conservative Offline MARL
496. ICLR 2026Why Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systems
497. ICLR 2026WideSearch: Benchmarking Agentic Broad Info-Seeking
498. ICLR 2026Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents
499. ICLR 2026Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning
500. ICLR 2026Zephyrus: An Agentic Framework for Weather Science

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.