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

1,983 papers, page 7 of 40

301. ICLR 2026Heterogeneous Agent Q-weighted Policy Optimization
302. ICLR 2026HeurekaBench: A Benchmarking Framework for AI Co-scientist
303. ICLR 2026HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization
304. ICLR 2026Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks
305. ICLR 2026Highly Efficient and Effective LLMs with Multi-Boolean Architectures
306. ICLR 2026Hilbert: Recursively Building Formal Proofs with Informal Reasoning
307. ICLR 2026HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
308. ICLR 2026Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation
309. ICLR 2026How Catastrophic is Your LLM? Certifying Risk in Conversation
310. ICLR 2026How Dark Patterns Manipulate Web Agents
311. ICLR 2026How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use
312. ICLR 2026Hubble: a Model Suite to Advance the Study of LLM Memorization
313. ICLR 2026Huxley-G\"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine
314. ICLR 2026ICaRus: Identical Cache Reuse for Efficient Multi-Model Inference
315. ICLR 2026ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases
316. ICLR 2026Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations
317. ICLR 2026Improving Code Localization with Repository Memory
318. ICLR 2026Improving Human-AI Coordination through Online Adversarial Training and Generative Models
319. ICLR 2026In Agents We Trust, but Who Do Agents Trust? Latent Preferences Steer LLM Generations
320. ICLR 2026In-The-Flow Agentic System Optimization for Effective Planning and Tool Use
321. ICLR 2026Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning
322. ICLR 2026Influence-Preserving Proxies for Gradient-Based Data Selection in LLM FineTuning
323. ICLR 2026InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents
324. ICLR 2026Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM Agents
325. ICLR 2026InnoGym: Benchmarking the Innovation Potential of AI Agents
326. ICLR 2026InnovatorBench: Evaluating Agents’ Ability to Conduct Innovative AI Research
327. ICLR 2026InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search
328. ICLR 2026Inter-Agent Relative Representations for Multi-Agent Option Discovery
329. ICLR 2026Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval
330. ICLR 2026Interactive Agents to Overcome Underspecificity in Software Engineering
331. ICLR 2026IR-Agent: Expert-Inspired LLM Agents for Structure Elucidation from Infrared Spectra
332. ICLR 2026IterResearch: Rethinking Long-Horizon Agents via Markovian State Reconstruction
333. ICLR 2026JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks
334. ICLR 2026Jet Expansions: Restructuring LLM Computation for Model Inspection
335. ICLR 2026JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generation
336. ICLR 2026Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
337. ICLR 2026K²-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device Control
338. ICLR 2026Kimi-Dev: Agentless Training as Skill Prior for SWE-agents
339. ICLR 2026KnowGuard: Knowledge-Driven Abstention for Multi-Round Clinical Reasoning
340. ICLR 2026KRAMABENCH: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes
341. ICLR 2026KVComm: Enabling Efficient LLM Communication through Selective KV Sharing
342. ICLR 2026Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
343. ICLR 2026Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text
344. ICLR 2026Learning Efficient and Interpretable Multi-Agent Communication
345. ICLR 2026Learning Global Hypothesis Space for Enhancing Synergistic Reasoning Chain
346. ICLR 2026Learning to Orchestrate Agents in Natural Language with the Conductor
347. ICLR 2026Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training
348. ICLR 2026Learning to Summarize by Learning to Quiz: Adversarial Agentic Collaboration for Long Document Summarization
349. ICLR 2026LeSTD: LLM Compression via Learning-based Sparse Tensor Decomposition
350. ICLR 2026Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification

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.