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 11 of 13

501. ICML 2026ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Management
502. ICML 2026Scaling Agentic Verifier for Competitive Coding
503. ICML 2026Scaling Long-Horizon Agent via Context Folding
504. ICML 2026Scaling Multi-Agent Environment Co-Design with Diffusion Models
505. ICML 2026Scaling Small Agents Through Strategy Auctions
506. ICML 2026Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning
507. ICML 2026Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers
508. ICML 2026Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation
509. ICML 2026SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes
510. ICML 2026SciAgentGym: Benchmarking Multi-Step Scientific Tool-Use in LLM Agents
511. ICML 2026SciNet: Evaluating AI Agents in Relation-Aware Scientific Literature Retrieval
512. ICML 2026Scout Before You Attend: Sketch-and-Walk Sparse Attention for Efficient LLM Inference
513. ICML 2026SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States
514. ICML 2026ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision
515. ICML 2026SE-GA: Memory-Augmented Self-Evolution for GUI Agents
516. ICML 2026SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience
517. ICML 2026Secure Multi-agent Reinforcement Learning for Service Systems with Affinity and Byzantine Nodes: Stability Analysis and Protection Design
518. ICML 2026Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation
519. ICML 2026SEDRAS: Symbolically Evaluated Deep Research And Science
520. ICML 2026Self-evolving LLM agents with in-distribution Optimization
521. ICML 2026Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA
522. ICML 2026SERA: Soft-Verified Efficient Repository Agents
523. ICML 2026Should I Have Expressed a Different Intent? Counterfactual Generation for LLM-Based Autonomous Control
524. ICML 2026SimpleMem: Efficient Lifelong Memory for LLM Agents
525. ICML 2026SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs
526. ICML 2026Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills
527. ICML 2026Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
528. ICML 2026SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
529. ICML 2026Small Agent Group is the Future of Digital Health
530. ICML 2026SOLAR for Offline MARL: Plateau-Triggered Potential Shaping under World-Model Uncertainty
531. ICML 2026SOPE: Situation-Aware and Statistically Indistinguishable Privacy Exfiltration for MCP-enabled Agents
532. ICML 2026SorryDB: Can AI Provers Complete Real-World Lean Theorems?
533. ICML 2026SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis
534. ICML 2026SPADA: A Verifiable Test-Driven Agent for Controllable Parametric CAD Assembly Generation
535. ICML 2026SPARe: Stacked Parallelism with Adaptive Reordering for Fault-Tolerant LLM Pretraining Systems with 100k+ GPUs
536. ICML 2026Sparks of Cooperative Reasoning: LLMs as Strategic Hanabi Agents
537. ICML 2026Sparse Topology-Aware Pairwise Scoring for Large-Scale Multi-Agent Reinforcement Learning
538. ICML 2026Speculative Safety Honeypot: Toward Proactive Defense Against Multi-turn Agent Attacks
539. ICML 2026Sponge Tool Attack: Stealthy Denial-of-Efficiency against Tool-Augmented Agentic Reasoning
540. ICML 2026SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning
541. ICML 2026StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning
542. ICML 2026Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games
543. ICML 2026Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
544. ICML 2026Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents
545. ICML 2026Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
546. ICML 2026Structurally Aligned Subtask-Level Memory for Software Engineering Agents
547. ICML 2026Student-Centered Distillation Narrows the Agentic Gap Between Small and Large LLMs
548. ICML 2026SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark
549. ICML 2026SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
550. ICML 2026SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models

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.