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

1,317 papers, page 2 of 27

51. NeurIPS 2026Agents' Last Exam
52. NeurIPS 2026AgentSSL: Can MLE Agents Leverage Unlabeled Data?
53. NeurIPS 2026AgentVista: Evaluating Multimodal Agent in Ultra-Challenging Realistic Visual Scenarios
54. NeurIPS 2026AGiR: Mitigating Gift Over-Reliance in Mixed-Motive Games
55. NeurIPS 2026Agree to Disagree: Multimodal Autonomous Negotiation and Calibration for Entity Representation Learning
56. NeurIPS 2026AIM: Adaptive Interaction in Multi-Agent Debate for Multimodal LLM Inference
57. NeurIPS 2026AIRA 2: Overcoming Bottlenecks in AI Research Agents
58. NeurIPS 2026AIRA-Compose: Agentic Discovery of Neural Architectures
59. NeurIPS 2026AirIAD: Agentic Iterative Reasoning for Industrial Anomaly Detection
60. NeurIPS 2026Aligning AI Teams
61. NeurIPS 2026An Empirical Study on Noisy Data and LLM Pretraining Loss Divergence
62. NeurIPS 2026Answering At Any Cost: Frontier LLMs Are Consequence-Insensitive
63. NeurIPS 2026ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport
64. NeurIPS 2026Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows
65. NeurIPS 2026Argus: A Cross-Regime Benchmark for the Transferability of Uncertainty Quantification in Computer-Use Agents
66. NeurIPS 2026ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge
67. NeurIPS 2026Articraft: An Agentic System for Scalable Articulated 3D Asset Generation
68. NeurIPS 2026ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation
69. NeurIPS 2026ASH: Agents that Self-Hone via Embodied Learning
70. NeurIPS 2026Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?
71. NeurIPS 2026Ask KG Agent: A Multi-Agent Framework for Code Localization Using Code and Knowledge Graphs
72. NeurIPS 2026ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
73. NeurIPS 2026AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents
74. NeurIPS 2026Assistive Dueling Bandits: No-Regret Algorithms for Assisting No-Regret Users
75. NeurIPS 2026AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
76. NeurIPS 2026ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
77. NeurIPS 2026Attack Selection In Agentic AI Control Evaluations Meaningfully Decreases Safety
78. NeurIPS 2026Auditing AI peer reviewers: a dose-response and false-positive benchmark on real scientific papers
79. NeurIPS 2026Auditing Evidence Framing at NeurIPS: A Decade-Scale Study of Accepted Papers
80. NeurIPS 2026AURA: An Autonomous Retouching Agent with Photographic Visual Thinking
81. NeurIPS 2026Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents
82. NeurIPS 2026AutoDataBench: How Far Are LLM Agents from Autonomously Engineering Post-Training Data Pipelines?
83. NeurIPS 2026AutoManifold: Agentic Design of Data Visualisation Algorithms via Manifold Embedding
84. NeurIPS 2026Automatically Refining Coding Rules for AI Coding Agents
85. NeurIPS 2026Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents
86. NeurIPS 2026Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents
87. NeurIPS 2026AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces
88. NeurIPS 2026AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
89. NeurIPS 2026Axiomatic Reinforcement Learning for Open Multi-Agent Systems from Shapley Axioms
90. NeurIPS 2026Ballad: Bandit-Based LLM Routing for Automated Heuristic Discovery
91. NeurIPS 2026BankerToolBench: Evaluating AI Agents in End-to-End Investment Banking Workflows
92. NeurIPS 2026Bayes-Sufficient Compression Is Not Enough: How Communication Helps in Multi-Agent Systems?
93. NeurIPS 2026Behavioral Probes for Information Flow in LLM Swarms
94. NeurIPS 2026BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems
95. NeurIPS 2026Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games
96. NeurIPS 2026Benchmark Recovery Does Not Certify a Frozen Tool-Trigger Contract After Quantization
97. NeurIPS 2026Benchmarking Open-Ended Multi-Agent Coordination in Language Agents
98. NeurIPS 2026Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns
99. NeurIPS 2026Beyond DSA: Conjugacy-based Comparison of Dynamical Systems
100. NeurIPS 2026Beyond High and Low: Evaluating Graded Cognitive Diversity in LLM Persona Simulations

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.