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

204 papers, page 4 of 5

151. ICLR 2025PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks
152. ICLR 2025PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration
153. ICLR 2025POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding
154. ICLR 2025Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation
155. ICLR 2025Preble: Efficient Distributed Prompt Scheduling for LLM Serving
156. ICLR 2025Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
157. ICLR 2025Rational Decision-Making Agent with Learning Internal Utility Judgment
158. ICLR 2025Re-Aligning Language to Visual Objects with an Agentic Workflow
159. ICLR 2025Reconstruction-Guided Policy: Enhancing Decision-Making through Agent-Wise State Consistency
160. ICLR 2025RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code
161. ICLR 2025Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
162. ICLR 2025Reward Learning from Multiple Feedback Types
163. ICLR 2025Robotouille: An Asynchronous Planning Benchmark for LLM Agents
164. ICLR 2025Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning
165. ICLR 2025ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL
166. ICLR 2025Scaling Autonomous Agents via Automatic Reward Modeling And Planning
167. ICLR 2025Scaling Large Language Model-based Multi-Agent Collaboration
168. ICLR 2025ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
169. ICLR 2025SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents
170. ICLR 2025Self-Evolving Multi-Agent Collaboration Networks for Software Development
171. ICLR 2025ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents
172. ICLR 2025Simulating Human-like Daily Activities with Desire-driven Autonomy
173. ICLR 2025Single-agent Poisoning Attacks Suffice to Ruin Multi-Agent Learning
174. ICLR 2025SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION
175. ICLR 2025Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows
176. ICLR 2025Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports
177. ICLR 2025SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget
178. ICLR 2025STAMP: Scalable Task- And Model-agnostic Collaborative Perception
179. ICLR 2025Steering Large Language Models between Code Execution and Textual Reasoning
180. ICLR 2025Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function Approximation
181. ICLR 2025Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search
182. ICLR 2025SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement
183. ICLR 2025Systems with Switching Causal Relations: A Meta-Causal Perspective
184. ICLR 2025TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
185. ICLR 2025Tool-Planner: Task Planning with Clusters across Multiple Tools
186. ICLR 2025ToolACE: Winning the Points of LLM Function Calling
187. ICLR 2025ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Models
188. ICLR 2025ToolGen: Unified Tool Retrieval and Calling via Generation
189. ICLR 2025TorchTitan: One-stop PyTorch native solution for production ready LLM pretraining
190. ICLR 2025Toward Efficient Multi-Agent Exploration With Trajectory Entropy Maximization
191. ICLR 2025Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
192. ICLR 2025Tractable Multi-Agent Reinforcement Learning through Behavioral Economics
193. ICLR 2025Trajectory-Class-Aware Multi-Agent Reinforcement Learning
194. ICLR 2025Trajectory-LLM: A Language-based Data Generator for Trajectory Prediction in Autonomous Driving
195. ICLR 2025Triples as the Key: Structuring Makes Decomposition and Verification Easier in LLM-based TableQA
196. ICLR 2025Video Action Differencing
197. ICLR 2025VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks
198. ICLR 2025Visual Agents as Fast and Slow Thinkers
199. ICLR 2025VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents
200. ICLR 2025Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation

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.