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 20 of 27

951. NeurIPS 2025MR. Video: MapReduce as an Effective Principle for Long Video Understanding
952. NeurIPS 2025MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in Oncology
953. NeurIPS 2025Multi-Agent Collaboration via Evolving Orchestration
954. NeurIPS 2025Multi-Agent Debate for LLM Judges with Adaptive Stability Detection
955. NeurIPS 2025Multi-Agent Imitation by Learning and Sampling from Factorized Soft Q-Function
956. NeurIPS 2025Multi-agent KTO: Enhancing Strategic Interactions of Large Language Model in Language Game
957. NeurIPS 2025Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration
958. NeurIPS 2025Multi-agent Markov Entanglement
959. NeurIPS 2025Multi-Agent Reinforcement Learning with Communication-Constrained Priors
960. NeurIPS 2025Multi-scale Temporal Prediction via Incremental Generation and Multi-agent Collaboration
961. NeurIPS 2025MURKA: Multi-Reward Reinforcement Learning with Knowledge Alignment for Optimization Tasks
962. NeurIPS 2025NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning
963. NeurIPS 2025On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning
964. NeurIPS 2025Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents
965. NeurIPS 2025Open-World Drone Active Tracking with Goal-Centered Rewards
966. NeurIPS 2025OpenCUA: Open Foundations for Computer-Use Agents
967. NeurIPS 2025OPHR: Mastering Volatility Trading with Multi-Agent Deep Reinforcement Learning
968. NeurIPS 2025Opinion Maximization in Social Networks by Modifying Internal Opinions
969. NeurIPS 2025OrbitZoo: Real Orbital Systems Challenges for Reinforcement Learning
970. NeurIPS 2025Oryx: a Scalable Sequence Model for Many-Agent Coordination in Offline MARL
971. NeurIPS 2025OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
972. NeurIPS 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
973. NeurIPS 2025OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis
974. NeurIPS 2025PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer
975. NeurIPS 2025Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
976. NeurIPS 2025PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization
977. NeurIPS 2025Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)
978. NeurIPS 2025PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions
979. NeurIPS 2025Planning with Quantized Opponent Models
980. NeurIPS 2025Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL
981. NeurIPS 2025Plasticity as the Mirror of Empowerment
982. NeurIPS 2025Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity
983. NeurIPS 2025PolarQuant: Leveraging Polar Transformation for Key Cache Quantization and Decoding Acceleration
984. NeurIPS 2025Policy Gradient Methods Converge Globally in Imperfect-Information Extensive-Form Games
985. NeurIPS 2025Pragmatic Heterogeneous Collaborative Perception via Generative Communication Mechanism
986. NeurIPS 2025Privacy Reasoning in Ambiguous Contexts
987. NeurIPS 2025Probably Approximately Precision and Recall Learning
988. NeurIPS 2025Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
989. NeurIPS 2025QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks
990. NeurIPS 2025R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization
991. NeurIPS 2025RADAR: Benchmarking Language Models on Imperfect Tabular Data
992. NeurIPS 2025Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Observation Delays
993. NeurIPS 2025ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding
994. NeurIPS 2025REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites
995. NeurIPS 2025ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents
996. NeurIPS 2025Regret Lower Bounds for Decentralized Multi-Agent Stochastic Shortest Path Problems
997. NeurIPS 2025Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies
998. NeurIPS 2025ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning
999. NeurIPS 2025Reparameterized LLM Training via Orthogonal Equivalence Transformation
1000. NeurIPS 2025RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving

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.