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

362 papers, page 6 of 8

251. NeurIPS 2025Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL
252. NeurIPS 2025Plasticity as the Mirror of Empowerment
253. NeurIPS 2025Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity
254. NeurIPS 2025PolarQuant: Leveraging Polar Transformation for Key Cache Quantization and Decoding Acceleration
255. NeurIPS 2025Policy Gradient Methods Converge Globally in Imperfect-Information Extensive-Form Games
256. NeurIPS 2025Pragmatic Heterogeneous Collaborative Perception via Generative Communication Mechanism
257. NeurIPS 2025Privacy Reasoning in Ambiguous Contexts
258. NeurIPS 2025Probably Approximately Precision and Recall Learning
259. NeurIPS 2025Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
260. NeurIPS 2025QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks
261. NeurIPS 2025R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization
262. NeurIPS 2025RADAR: Benchmarking Language Models on Imperfect Tabular Data
263. NeurIPS 2025Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Observation Delays
264. NeurIPS 2025ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding
265. NeurIPS 2025REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites
266. NeurIPS 2025ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents
267. NeurIPS 2025Regret Lower Bounds for Decentralized Multi-Agent Stochastic Shortest Path Problems
268. NeurIPS 2025Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies
269. NeurIPS 2025ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning
270. NeurIPS 2025Reparameterized LLM Training via Orthogonal Equivalence Transformation
271. NeurIPS 2025RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving
272. NeurIPS 2025Representation Consistency for Accurate and Coherent LLM Answer Aggregation
273. NeurIPS 2025Retro-R1: LLM-based Agentic Retrosynthesis
274. NeurIPS 2025RF-Agent: Automated Reward Function Design via Language Agent Tree Search
275. NeurIPS 2025RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
276. NeurIPS 2025RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills
277. NeurIPS 2025Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
278. NeurIPS 2025Role-aware Multi-agent Reinforcement Learning for Coordinated Emergency Traffic Control
279. NeurIPS 2025SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
280. NeurIPS 2025Sample-Efficient Tabular Self-Play for Offline Robust Reinforcement Learning
281. NeurIPS 2025Scalable Neural Incentive Design with Parameterized Mean-Field Approximation
282. NeurIPS 2025Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis
283. NeurIPS 2025SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent
284. NeurIPS 2025SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
285. NeurIPS 2025SE-GUI: Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning
286. NeurIPS 2025SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks
287. NeurIPS 2025Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition
288. NeurIPS 2025SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents
289. NeurIPS 2025Seeking and Updating with Live Visual Knowledge
290. NeurIPS 2025Self-Challenging Language Model Agents
291. NeurIPS 2025Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks
292. NeurIPS 2025Self-Guided Hierarchical Exploration for Generalist Foundation Model Web Agents
293. NeurIPS 2025Sequential Multi-Agent Dynamic Algorithm Configuration
294. NeurIPS 2025ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling
295. NeurIPS 2025Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents
296. NeurIPS 2025Simulating Society Requires Simulating Thought
297. NeurIPS 2025Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models
298. NeurIPS 2025SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds
299. NeurIPS 2025SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
300. NeurIPS 2025SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific Sketches

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.