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

817 papers, page 9 of 17

401. ICLR 2026SPACeR: Self-Play Anchoring with Centralized Reference Models
402. ICLR 2026SpareTrain: Fault-Tolerant LLM Training via Low-Cost Dual Modular Redundancy
403. ICLR 2026Speculative Actions: A Lossless Framework for Faster AI Agents
404. ICLR 2026Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives
405. ICLR 2026Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations
406. ICLR 2026SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
407. ICLR 2026SR-Scientist: Scientific Equation Discovery With Agentic AI
408. ICLR 2026SSVPO: Effective Step-Level Credit Assignment for RL Training of Language Models
409. ICLR 2026ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents
410. ICLR 2026STAIRS-Former: Spatio-Temporal Attention with Interleaved Recursive Structure TransFormer for Offline Mulit-task Multi-agent Reinforcement Learning
411. ICLR 2026STARK: Strategic Team of Agents for Refining Kernels
412. ICLR 2026Steering and Rectifying Latent representation manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection
413. ICLR 2026StepORLM: A Self-Evolving Framework With Generative Process Supervision For Operations Research Language Models
414. ICLR 2026Stochastic Self-Organization in Multi-Agent Systems
415. ICLR 2026Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems
416. ICLR 2026Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters
417. ICLR 2026Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs
418. ICLR 2026Structurally Human, Semantically Biased: Detecting LLM-Generated References with Embeddings and GNNs
419. ICLR 2026Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
420. ICLR 2026SWE-RM: Execution-free Feedback for Software Engineering Agents
421. ICLR 2026SWERank: Software Issue Localization with Code Ranking
422. ICLR 2026SynthWorlds: Controlled Parallel Worlds for Disentangling Reasoning and Knowledge in Language Models
423. ICLR 2026SysMoBench: Evaluating AI on Formally Specifying Complex Real-World Systems
424. ICLR 2026Systematic Biosafety Evaluation of DNA Language Models under Jailbreak Attacks
425. ICLR 2026Talk, Evaluate, Diagnose: User-aware Agent Evaluation with Automated Error Analysis
426. ICLR 2026Taming the Fragility of KV Cache Eviction in LLM Inference
427. ICLR 2026TaskCraft: Automated Generation of Agentic Tasks
428. ICLR 2026Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
429. ICLR 2026Test-Time Adaptation for LLM Agents via Environment Interaction
430. ICLR 2026Textual Bayes: Quantifying Uncertainty in LLM-Based Systems
431. ICLR 2026Textual Equilibrium Propagation for Deep Compound AI Systems
432. ICLR 2026The Alignment Waltz: Jointly Training Agents to Collaborate for Safety
433. ICLR 2026The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm
434. ICLR 2026The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
435. ICLR 2026The Matthew Effect of AI Programming Assistants: A Hidden Bias in Software Evolution
436. ICLR 2026The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
437. ICLR 2026Thinking as Society: Multi-Social-Agent Self-Distillation for Multimodal Misinformation Detection
438. ICLR 2026THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning
439. ICLR 2026Thought Branches: Interpreting LLM Reasoning Requires Resampling
440. ICLR 2026Thyme: Think Beyond Images
441. ICLR 2026TimeSeriesExamAgent: Creating TimeSeries Reasoning Benchmarks at Scale
442. ICLR 2026TIPS: Turn-level Information-Potential Reward Shaping for Search-Augmented LLMs
443. ICLR 2026To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models
444. ICLR 2026ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction
445. ICLR 2026ToolTree: Efficient LLM Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning
446. ICLR 2026ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language Models
447. ICLR 2026Toward Efficient Exploration by Large Language Model Agents
448. ICLR 2026Towards Multimodal Data-Driven Scientific Discovery Powered by LLM Agents
449. ICLR 2026Towards Personalized Deep Research: Benchmarks and Evaluations
450. ICLR 2026Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling

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.