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

729 papers, page 9 of 15

401. NeurIPS 2026Mind the Gap: Information Disadvantage as a Learning Signal in Cooperative MARL
402. NeurIPS 2026MindGames:A Multi-Agent Benchmark and Trajectory Dataset for Evaluating Social and Strategic Reasoning in LLMs
403. NeurIPS 2026MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents
404. NeurIPS 2026MiniPIC: Flexible Position-Independent Caching in <100LOC
405. NeurIPS 2026Mirror, Mirror on the Wall: Can VLM Agents Tell Who They Are at All?
406. NeurIPS 2026MLLMs Fail to Refuse when Using Tools Agentically
407. NeurIPS 2026MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
408. NeurIPS 2026MMGraph-Agent: Agentic Multimodal RAG via Cache-Inspired Multimodal Knowledge HyperGraphs
409. NeurIPS 2026MMSkills: Towards Multimodal Skills for General Visual Agents
410. NeurIPS 2026Mode-Controlled Policy Optimization: A Geometry-Aware Recipe for LLM Post-Training
411. NeurIPS 2026Model Incrimination: Investigating Whether Concerning Behavior Reflects Misalignment
412. NeurIPS 2026Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use
413. NeurIPS 2026Modelling Opinion Dynamics at Scale with Deep MARL
414. NeurIPS 2026Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation
415. NeurIPS 2026MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens
416. NeurIPS 2026More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models
417. NeurIPS 2026More Value per Key: Asymmetric Sparse Attention for Faster LLM Decoding
418. NeurIPS 2026MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
419. NeurIPS 2026MOSAIC: Scaling Long-Horizon Language Agents via Multi-Scale Adaptive Inference Control
420. NeurIPS 2026Motion Forcing: Decoupling Ego and Object Motion via Sparse Inputs for Structured Video Generation
421. NeurIPS 2026MPCI-Bench: A Benchmark for Multimodal Pairwise Contextual Integrity Privacy Evaluation of Language Model Agents
422. NeurIPS 2026Multi-agent Collaboration with State Management
423. NeurIPS 2026Multi-Agent Coordination via Support-Preserving Distillation
424. NeurIPS 2026Multi-bit LLM Watermarking with Certified Semantic Distortion
425. NeurIPS 2026MultiSTEVE-1s: A Model Zoo and Interpretability Suite for Instruction-Following Vision Agents
426. NeurIPS 2026NARRA-Gym for Evaluating Interactive Narrative Agents
427. NeurIPS 2026Narrowing the Collaboration Gap, Probably
428. NeurIPS 2026Nautilus: From One Prompt to Plug-and-Play Robot Learning
429. NeurIPS 2026Need-Aware Multi-Objective Reinforcement Learning for Emotionally Intelligent LLM Agents
430. NeurIPS 2026Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
431. NeurIPS 2026NEST: Nascent Encoded Steganographic Thoughts
432. NeurIPS 2026NestRL: A Nested Training Regime for Mutual Adaptation in Human–AI Teaming
433. NeurIPS 2026NeSyKC: Neurosymbolic Knowledge Compilation For Lifelong Learning Embodied Agents
434. NeurIPS 2026NesyProAct: Proactive Neural-Symbolic Control for Web Agents
435. NeurIPS 2026NINJA: A Navigator–Inspector Joint Architecture for Context-Efficient Issue Localization
436. NeurIPS 2026NitroBox: Lightning-Fast Sandbox for Large-Scale RL Training
437. NeurIPS 2026No Model Required: Text Entropy Rate Filtering Prevents Iterative Fine-Tuning Collapse
438. NeurIPS 2026Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems
439. NeurIPS 2026Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness
440. NeurIPS 2026ODDR: One-Step Deshadow Diffusion via Reward Guidance
441. NeurIPS 2026OfficeInstruct: A Dataset for Tool-Augmented Office Agents on Long-Trajectory Generative Tasks
442. NeurIPS 2026Offline Preference-Based Trajectory Evaluation
443. NeurIPS 2026On Data Engineering for Scaling LLM Terminal Capabilities
444. NeurIPS 2026On the Impact of Side-Information in Bandit Learning: More is Not Always Merrier
445. NeurIPS 2026On the Nonlinearity of Learning Rate Scaling for LLM Training
446. NeurIPS 2026One Adapter For All: Towards Generalizable Many-To-One Domain Adaptation In Heterogeneous Collaborative Perception
447. NeurIPS 2026One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning
448. NeurIPS 2026Online Fair Division Meets Reordering Buffers
449. NeurIPS 2026Online Learning in Stabilized Linear Dynamical Games with Adversarial Disturbances
450. NeurIPS 2026OntoPlan: An Ontology-Grounded Scene Representation and Agentic Framework for Scalable Robot Task Planning

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.