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

729 papers, page 4 of 15

151. NeurIPS 2026Control Charts for Multi-Agent Systems
152. NeurIPS 2026Controllable Road Marking Generation
153. NeurIPS 2026Convergence Guarantees for Federated SARSA with Local Training and Heterogeneous Agents
154. NeurIPS 2026Cooperative Multi-Agent Reinforcement Learning via Epigraph-Form Guided Exploration
155. NeurIPS 2026Coordinating Hundreds of RL Agents through Scalable Inference-Time Search
156. NeurIPS 2026Coordination Connectivity: Shared Initialization Shapes the Joint-Policy Landscape in MARL
157. NeurIPS 2026COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams
158. NeurIPS 2026Counterfactual Distillation: Internalizing Reflective Experience into LLM Agent
159. NeurIPS 2026CounterStrike-1K: A Multi-Perspective Dataset of Professional Gameplay for World Modeling
160. NeurIPS 2026CoupledFlow: One-Step Neural Operators for Coupled Multi-Physics PDEs
161. NeurIPS 2026Coupling-Aware Reinforcement Learning for Co-Evolving Graph Games
162. NeurIPS 2026CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter
163. NeurIPS 2026CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
164. NeurIPS 2026CREF: Forecasting Benchmarks for the Age of Agents
165. NeurIPS 2026Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse
166. NeurIPS 2026Cross-User Poisoning: User-Task Boundary Failures in Multi-User Collaborative Language Agents
167. NeurIPS 2026CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness
168. NeurIPS 2026CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging
169. NeurIPS 2026CURE: Coupled User-Grouped Reinforcement Learning for Cross-Domain Recommendation with Non-Overlapping Users
170. NeurIPS 2026CyberDualEval: Measuring Dual-Use Cyber Risks in Frontier Language Models
171. NeurIPS 2026CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios
172. NeurIPS 2026DAGent: Evaluate-then-Grow Planning for Deep Research Agents
173. NeurIPS 2026DDACOM: Dual-Decoupled Adaptive Communication for Multi-Agent Reinforcement Learning under Dynamic Networks
174. NeurIPS 2026DDBench: A Benchmark for Agentic Debugging on Distributed Systems
175. NeurIPS 2026DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems
176. NeurIPS 2026Decentralized Multi-Goal Multi-Agent Pathfinding with Spatial Prior and Neighbor Intent Prediction
177. NeurIPS 2026Decentralized Q-Learning in Markov Potential Games
178. NeurIPS 2026Deep Reasoning in General Purpose Agents via Structured Meta-Cognition
179. NeurIPS 2026Deep Research as Rubric
180. NeurIPS 2026DeepArrhythmia: Segment-Contextualized ECG Arrhythmia Classification via Selective Evidence Acquisition
181. NeurIPS 2026Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents
182. NeurIPS 2026DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents
183. NeurIPS 2026DICE: Decoupling Capability from Intervention Necessity in LLM Tutoring
184. NeurIPS 2026Differentiable Belief-based Opponent Shaping
185. NeurIPS 2026DIS-Bench: Evaluating LLMs on System Testing via Directed Input Synthesis
186. NeurIPS 2026Discovering Phase Space Structure in Learned Hamiltonian Systems
187. NeurIPS 2026DiscoverPhysics: Benchmarking LLMs for out-of-the-box scientific thinking
188. NeurIPS 2026DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems?
189. NeurIPS 2026Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests
190. NeurIPS 2026Do Joint Audio-Video Generation Models Understand Physics?
191. NeurIPS 2026DocAtlas: Long-Document Understanding as Mutable-State Interaction
192. NeurIPS 2026Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble Selection
193. NeurIPS 2026Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents
194. NeurIPS 2026Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
195. NeurIPS 2026DualWorldBench: Can Agents Plan Deliveries across Symbolic and Grounded Worlds?
196. NeurIPS 2026ECG Dataset with Multi-Expert Annotations and Delineations
197. NeurIPS 2026Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
198. NeurIPS 2026Effective Knowledge Conflict Detection via Joint Agentic Optimization
199. NeurIPS 2026Efficient evaluation and error pattern discovery for blackbox AI systems
200. NeurIPS 2026Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management

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.