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 6 of 66

251. ICLR 2026Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents
252. ICLR 2026Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs
253. ICLR 2026Estimating Worst-Case Frontier Risks of Open-Weight LLMs
254. ICLR 2026Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
255. ICLR 2026EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems
256. ICLR 2026EXP-Bench: Can AI Conduct AI Research Experiments?
257. ICLR 2026Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis
258. ICLR 2026Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
259. ICLR 2026Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMs
260. ICLR 2026Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs
261. ICLR 2026FeatureBench: Benchmarking Agentic Coding for Complex Feature Development
262. ICLR 2026Fewer Weights, More Problems: A Practical Attack on LLM Pruning
263. ICLR 2026FHE-Coder: Secure Agentic Code Generation for Fully Homomorphic Encryption
264. ICLR 2026Financial fraud collusion among generative AI agents in social networks
265. ICLR 2026FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents
266. ICLR 2026FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning
267. ICLR 2026Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution
268. ICLR 2026FlowSearcher: Synthesizing Memory-Guided Agentic Workflows for Web Information Seeking
269. ICLR 2026FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
270. ICLR 2026From Assistant to Independent Developer — Are GPTs Ready for Software Development?
271. ICLR 2026From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents
272. ICLR 2026From Conversation to Query Execution: Benchmarking User and Tool Interactions for EHR Database Agents
273. ICLR 2026From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical Visualization
274. ICLR 2026From Embedding to Control: Representations for Stochastic Multi-Object Systems
275. ICLR 2026From Medical Records to Diagnostic Dialogues: A Clinical-Grounded Approach and Dataset for Psychiatric Comorbidity
276. ICLR 2026From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking
277. ICLR 2026From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents
278. ICLR 2026From Static Benchmarks to Dynamic Protocol: Agent-Centric Text Anomaly Detection for Evaluating LLM Reasoning
279. ICLR 2026From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning
280. ICLR 2026FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction
281. ICLR 2026Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments
282. ICLR 2026GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning
283. ICLR 2026GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks
284. ICLR 2026GEM: A Gym for Generalist LLMs
285. ICLR 2026Generalizable End-to-End Tool-Use RL with Synthetic CodeGym
286. ICLR 2026GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
287. ICLR 2026GhostEI-Bench: Do Mobile Agent Resilience to Environmental Injection in Dynamic On-Device Environments?
288. ICLR 2026Gistify: Codebase-Level Understanding via Runtime Execution
289. ICLR 2026GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent System
290. ICLR 2026Go-Browse: Training Web Agents with Structured Exploration
291. ICLR 2026Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems
292. ICLR 2026Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration
293. ICLR 2026GraphPlanner: Graph-Based Agentic Routing for LLMs
294. ICLR 2026Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test
295. ICLR 2026GT-Space: Enhancing Heterogeneous Collaborative Perception with Ground Truth Feature Space
296. ICLR 2026GTA1: GUI Test-time Scaling Agent
297. ICLR 2026GUI-Shift: Enhancing VLM-Based GUI Agents through Self-supervised Reinforcement Learning
298. ICLR 2026HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities
299. ICLR 2026HAMLET: Hyperadaptive Agent-based Modeling for Live Embodied Theatrics
300. ICLR 2026Helmsman: Autonomous Synthesis of Federated Learning Systems via Collaborative LLM Agents

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.