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

640 papers, page 3 of 13

101. ICML 2026Calibrating Conservatism for Scalable Oversight
102. ICML 2026Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use
103. ICML 2026Can LLM Agents Stick to the Script? Modeling Commitment in Interactive Narratives
104. ICML 2026CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training
105. ICML 2026CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments
106. ICML 2026Catch-22: On the Fundamental Tradeoff Between Detectability and Robustness in LLM Watermarking
107. ICML 2026Causal Detection of Multi-Step LLM Agent Attacks
108. ICML 2026CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution
109. ICML 2026CausalGame: Benchmarking Causal Thinking of LLM Agents in Games
110. ICML 2026CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception
111. ICML 2026CCLRec: Consensus-driven Contrastive Learning for LLM-enhanced Graph Recommendation
112. ICML 2026CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding
113. ICML 2026CGRiC: Compositional Risk Certification for Structured LLM Outputs
114. ICML 2026Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
115. ICML 2026Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models
116. ICML 2026CINOC: Cardinality-Invariant Neural Operator Policies for Scalable PDE Control
117. ICML 2026Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation
118. ICML 2026CLIMB: Taming the LoRA Residency Cliff in Multi-LoRA Serving
119. ICML 2026Clipping Low-Probability Tokens in SFT Yields a Generalizable Initialization for RL
120. ICML 2026Closing the Expression Gap in LLM Instructions via Socratic Questioning
121. ICML 2026Closing the Loop: Universal Repository Representation with RPG-Encoder
122. ICML 2026Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents
123. ICML 2026CocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcement Learning
124. ICML 2026CoDA-Bench: Can Code Agents Handle Data-Intensive Tasks?
125. ICML 2026Code2Video: A Code-centric Paradigm for Educational Video Creation
126. ICML 2026Code2Worlds: Empowering Coding LLMs for 4D World Generation
127. ICML 2026CodeTaste: Can LLMs Generate Human-Level Code Refactorings?
128. ICML 2026CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement
129. ICML 2026Collaborative Disagreement Resolution for Scalable Oversight
130. ICML 2026CoME: Empowering Channel-of-Mobile-Experts with Informative Hybrid-Capabilities Reasoning
131. ICML 2026CoMem: Context Management with A Decoupled Long-Context Model
132. ICML 2026ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox
133. ICML 2026CONCUR: High-Throughput Agentic Batch Inference of LLM via Congestion-Based Concurrency Control
134. ICML 2026Conflict-Aware Adaptive Alignment for LLM Hallucination Mitigation
135. ICML 2026ConServe: Fine-Grained GPU Harvesting for LLM Online and Offline Co-Serving
136. ICML 2026Constitutional Black-Box Monitoring for Scheming in LLM Agents
137. ICML 2026Contextualized Privacy Defense for LLM Agents
138. ICML 2026Continual GUI Agents
139. ICML 2026Controlled LLM Training on Spectral Sphere
140. ICML 2026Conversation for Non-verifiable Learning: Self-Evolving Large Language Models through Meta-Evaluation
141. ICML 2026ConvexBench: Can LLMs Recognize Convex Functions?
142. ICML 2026CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas
143. ICML 2026CooT: Learning to Coordinate In-Context with Coordination Transformers
144. ICML 2026CoPE: A Framework for Optimizing Coordination between Planning and Execution in LLM-based Agents
145. ICML 2026Copyright-Bench: Agentic Evaluation of Copyright Law Compliance
146. ICML 2026CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systems
147. ICML 2026CUARewardBench: A Benchmark for Evaluating Reward Models for Computer-Using Agents
148. ICML 2026CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability
149. ICML 2026CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities
150. ICML 2026CyberJurors: A Multi-Agent Simulation Task for E-Commerce Disputes Verdict

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.