The Research Desk.

The most upvoted and starred AI research crossing the community today.

Last Brew Time: May 19, 2026, 7:31 AM PT

AlphaXiv Trending

Reinforcement Learning
Self-Distilled Agentic Reinforcement Learning
AlphaXiv
145

Self-Distilled Agentic Reinforcement Learning

Zhengxi Lu, Zhiyuan Yao, Zhuowen Han

Zhejiang University, Tsinghua University

VGGT- Ω Ω
AlphaXiv
133

VGGT- Ω Ω

Jianyuan Wang, Minghao Chen, Shangzhan Zhang

NLP
𝛿 δ-mem: Efficient Online Memory for Large Language Models
AlphaXiv
113

𝛿 δ-mem: Efficient Online Memory for Large Language Models

Jingdi Lei, Di Zhang, Junxian Li

NLP
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
AlphaXiv
107

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Haoyi Zhu, Haozhe Liu, Yuyang Zhao

NVIDIA

Reinforcement Learning
FutureSim: Replaying World Events to Evaluate Adaptive Agents
AlphaXiv
97

FutureSim: Replaying World Events to Evaluate Adaptive Agents

Shashwat Goel, Nikhil Chandak, Arvindh Arun

Reinforcement Learning
Is Grep All You Need? How Agent Harnesses Reshape Agentic Search
AlphaXiv
64

Is Grep All You Need? How Agent Harnesses Reshape Agentic Search

Sahil Sen, Akhil Kasturi, Elias Lumer

HuggingFace Daily Papers

Reinforcement Learning
CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
HuggingFace
14

CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?

Haolin Chen, Deon Metelski, Leon Qi, Tao Xia, Joonyul Lee

actAVA AI

Reinforcement Learning
TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents
HuggingFace
2

TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents

Zhiqiang Liu, Wenhui Dong, Yilang Tan, Yuwen Qu, Haochen Yin

Pi3AI

Reinforcement Learning
Evaluating Cognitive Age Alignment in Interactive AI Agents
HuggingFace
1

Evaluating Cognitive Age Alignment in Interactive AI Agents

Yifan Shen, Jiawen Zhang, Jian Xu, Junho Kim, Ismini Lourentzou

PediaMed AI

Reinforcement Learning
MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents
HuggingFace
1

MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents

Ziyun Zeng, Hang Hua, Bocheng Zou, Mu Cai, Rogerio Feris

Computer Vision
VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation
HuggingFace
1

VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation

Yiming Zhao, Yu Zeng, Wenxuan Huang, Zhen Fang, Qing Miao

Efficiency
E-PMQ: Expert-Guided Post-Merge Quantization with Merged-Weight Anchoring
HuggingFace
1

E-PMQ: Expert-Guided Post-Merge Quantization with Merged-Weight Anchoring

Wenjun Wang, Yanggan Gu, Shuo Cai, Yuanyi Wang, Pengkai Wang

The Hong Kong Polytechnic University