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

500 papers, page 3 of 10

101. ICLR 2026DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
102. ICLR 2026DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
103. ICLR 2026Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents
104. ICLR 2026Demystifying Deep Search: A Holistic Evaluation with Hint-free Multi-Hop Questions and Factorised Metrics
105. ICLR 2026Denoising Neural Reranker for Recommender Systems
106. ICLR 2026Detection of unknown unknowns in autonomous systems
107. ICLR 2026DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle
108. ICLR 2026Discovering Hierarchical Software Engineering Agents via Bandit Optimization
109. ICLR 2026Discovering Novel LLM Experts via Task-Capability Coevolution
110. ICLR 2026DiSRouter: Distributed Self-Routing for LLM Selections
111. ICLR 2026Distributionally Robust Cooperative Multi-agent Reinforcement Learning with Value Factorization
112. ICLR 2026Divide, Harmonize, Then Conquer It: Shooting Multi-Commodity Flow Problems with Multimodal Language Models
113. ICLR 2026Do Large Language Models Know What They Are Capable Of?
114. ICLR 2026Do LLM Agents Know How to Ground, Recover, and Assess? Evaluating Epistemic Competence in Information-Seeking Agents
115. ICLR 2026Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning
116. ICLR 2026Don't Just Fine-tune the Agent, Tune the Environment
117. ICLR 2026Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect Personas
118. ICLR 2026DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems
119. ICLR 2026DRBench: A Realistic Benchmark for Enterprise Deep Research
120. ICLR 2026DreamPhase: Offline Imagination and Uncertainty-Guided Planning for Large-Language-Model Agents
121. ICLR 2026Drugging the Undruggable: Benchmarking and Modeling Fragment-Based Screening
122. ICLR 2026Dual-Scale World Models for LLM Agents towards Hard-Exploration Problems
123. ICLR 2026DualMap: Enabling Both Cache Affinity and Load Balancing for Distributed LLM Serving
124. ICLR 2026Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
125. ICLR 2026Dynamic Speculative Agent Planning
126. ICLR 2026Earth-Agent: Unlocking the Full Landscape of Earth Observation with Agents
127. ICLR 2026Efficient Agent Training for Computer Use
128. ICLR 2026Eigen-1: Scientific Reasoning through Adaptive Multi-Agent Refinement and Monitor-based RAG
129. ICLR 2026Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization
130. ICLR 2026Emergent Coordination in Multi-Agent Language Models
131. ICLR 2026Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking
132. ICLR 2026Empowering LLM Tool Invocation with Tool-call Reward Model
133. ICLR 2026Empowering Multi-Robot Cooperation via Sequential World Models
134. ICLR 2026Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World
135. ICLR 2026Enhancing Agentic Search via Data Synthesis on Hierarchical Constraint Satisfaction
136. ICLR 2026Enhancing Complex Symbolic Logical Rea­soning of Large Language Models via Sparse Multi-Agent Debate
137. ICLR 2026Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents
138. ICLR 2026Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs
139. ICLR 2026Estimating Worst-Case Frontier Risks of Open-Weight LLMs
140. ICLR 2026Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
141. ICLR 2026EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems
142. ICLR 2026EXP-Bench: Can AI Conduct AI Research Experiments?
143. ICLR 2026Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis
144. ICLR 2026Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
145. ICLR 2026Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMs
146. ICLR 2026Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs
147. ICLR 2026FeatureBench: Benchmarking Agentic Coding for Complex Feature Development
148. ICLR 2026Fewer Weights, More Problems: A Practical Attack on LLM Pruning
149. ICLR 2026FHE-Coder: Secure Agentic Code Generation for Fully Homomorphic Encryption
150. ICLR 2026Financial fraud collusion among generative AI agents in social networks

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.