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

3,266 papers, page 48 of 66

2351. ICML 2025Position: Truly Self-Improving Agents Require Intrinsic Metacognitive Learning
2352. ICML 2025Position: Uncertainty Quantification Needs Reassessment for Large Language Model Agents
2353. ICML 2025Position: We Need An Algorithmic Understanding of Generative AI
2354. ICML 2025Prediction-Aware Learning in Multi-Agent Systems
2355. ICML 2025Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents
2356. ICML 2025Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty
2357. ICML 2025Proposer-Agent-Evaluator (PAE): Autonomous Skill Discovery For Foundation Model Internet Agents
2358. ICML 2025Provably Efficient Algorithm for Best Scoring Rule Identification in Online Principal-Agent Information Acquisition
2359. ICML 2025Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction
2360. ICML 2025QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search
2361. ICML 2025R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning
2362. ICML 2025RE-Bench: Evaluating Frontier AI R&D Capabilities of Language Model Agents against Human Experts
2363. ICML 2025Reflection-Bench: Evaluating Epistemic Agency in Large Language Models
2364. ICML 2025Reidentify: Context-Aware Identity Generation for Contextual Multi-Agent Reinforcement Learning
2365. ICML 2025Reinforce LLM Reasoning through Multi-Agent Reflection
2366. ICML 2025RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing
2367. ICML 2025ResearchTown: Simulator of Human Research Community
2368. ICML 2025Revisiting Cooperative Off-Policy Multi-Agent Reinforcement Learning
2369. ICML 2025Risk-Sensitive Theory of Mind: Coordinating with Agents of Unknown Bias using Cumulative Prospect Theory
2370. ICML 2025RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning
2371. ICML 2025Robust Multi-Agent Reinforcement Learning with Stochastic Adversary
2372. ICML 2025Robust Multi-bit Text Watermark with LLM-based Paraphrasers
2373. ICML 2025Robust Noise Attenuation via Adaptive Pooling of Transformer Outputs
2374. ICML 2025Sable: a Performant, Efficient and Scalable Sequence Model for MARL
2375. ICML 2025SafeArena: Evaluating the Safety of Autonomous Web Agents
2376. ICML 2025Self-Play $Q$-Learners Can Provably Collude in the Iterated Prisoner's Dilemma
2377. ICML 2025ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
2378. ICML 2025Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models
2379. ICML 2025Solving Zero-Sum Convex Markov Games
2380. ICML 2025Star Attention: Efficient LLM Inference over Long Sequences
2381. ICML 2025StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models
2382. ICML 2025SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training
2383. ICML 2025SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
2384. ICML 2025SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering
2385. ICML 2025Synthesizing Software Engineering Data in a Test-Driven Manner
2386. ICML 2025The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models
2387. ICML 2025The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
2388. ICML 2025The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability
2389. ICML 2025The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data
2390. ICML 2025Tokenized Bandit for LLM Decoding and Alignment
2391. ICML 2025Tool Unlearning for Tool-Augmented LLMs
2392. ICML 2025Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning
2393. ICML 2025Towards Practical Defect-Focused Automated Code Review
2394. ICML 2025Training a Generally Curious Agent
2395. ICML 2025Training Software Engineering Agents and Verifiers with SWE-Gym
2396. ICML 2025UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
2397. ICML 2025UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
2398. ICML 2025Unbiased Evaluation of Large Language Models from a Causal Perspective
2399. ICML 2025Understanding Bias Reinforcement in LLM Agents Debate
2400. ICML 2025UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent

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.