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

784 papers, page 9 of 16

401. ICML 2025SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering
402. ICML 2025Synthesizing Software Engineering Data in a Test-Driven Manner
403. ICML 2025The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models
404. ICML 2025The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
405. ICML 2025The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability
406. ICML 2025The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data
407. ICML 2025Tokenized Bandit for LLM Decoding and Alignment
408. ICML 2025Tool Unlearning for Tool-Augmented LLMs
409. ICML 2025Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning
410. ICML 2025Towards Practical Defect-Focused Automated Code Review
411. ICML 2025Training a Generally Curious Agent
412. ICML 2025Training Software Engineering Agents and Verifiers with SWE-Gym
413. ICML 2025UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
414. ICML 2025UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
415. ICML 2025Unbiased Evaluation of Large Language Models from a Causal Perspective
416. ICML 2025Understanding Bias Reinforcement in LLM Agents Debate
417. ICML 2025UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent
418. ICML 2025What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities
419. ICML 2025Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
420. ICML 2025Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
421. ICML 2025Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning
422. ICML 2025µnit Scaling: Simple and Scalable FP8 LLM Training
423. NeurIPS 20253DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
424. NeurIPS 20254KAgent: Agentic Any Image to 4K Super-Resolution
425. NeurIPS 2025A machine learning approach that beats Rubik's cubes
426. NeurIPS 2025A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond
427. NeurIPS 2025A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
428. NeurIPS 2025A-Mem: Agentic Memory for LLM Agents
429. NeurIPS 2025Abstract Counterfactuals for Language Model Agents
430. NeurIPS 2025AC-LoRA: (Almost) Training-Free Access Control Aware Multi-Modal LLMs
431. NeurIPS 2025Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning
432. NeurIPS 2025Adaptive Preference Arithmetic: A Personalized Agent with Adaptive Preference Arithmetic for Dynamic Preference Modeling
433. NeurIPS 2025Adaptively Coordinating with Novel Partners via Learned Latent Strategies
434. NeurIPS 2025AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios
435. NeurIPS 2025AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents
436. NeurIPS 2025AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement
437. NeurIPS 2025AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
438. NeurIPS 2025Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents
439. NeurIPS 2025Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem Solving
440. NeurIPS 2025AGENTIF: Benchmarking Large Language Models Instruction Following Ability in Agentic Scenarios
441. NeurIPS 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
442. NeurIPS 2025AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
443. NeurIPS 2025Agents Robust to Distribution Shifts Learn Causal World Models Even Under Mediation
444. NeurIPS 2025AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks
445. NeurIPS 2025AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
446. NeurIPS 2025AI-Researcher: Autonomous Scientific Innovation
447. NeurIPS 2025ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering
448. NeurIPS 2025Among Us: A Sandbox for Measuring and Detecting Agentic Deception
449. NeurIPS 2025APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay
450. NeurIPS 2025APOLLO: Automated LLM and Lean Collaboration for Advanced Formal Reasoning

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.