The Research Desk.

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

Last Brew Time: Aug 23, 2026, 10:43 AM PT

X.com Research Buzz

NLP
Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems
X.com
7366

Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems

Vassilis Papadopoulos, McNair Shah, Sam Zimmerman, Jack Lindsey

Anthropic, EPFL

Mathematics in the age of AI
X.com
2690

Mathematics in the age of AI

Terence Tao

AlphaXiv Trending

Mathematics in the age of AI
AlphaXiv
435

Mathematics in the age of AI

Terence Tao

Address: UCLA Department of Mathematics, Los Angeles, CA 90095-1555, UCLA Department of Mathematics, Los Angeles, CA 90095-1555

Recirculation
AlphaXiv
209

Recirculation

Michael C. Mozer, Shoaib Ahmed Siddiqui, Danny Sawyer

Thanks: Work performed while a student researcher at DeepMind, Michael C. MozerGoogle DeepMind, Shoaib Ahmed SiddiquiGoogle DeepMind, Danny SawyerGoogle DeepMind, Rosanne LiuGoogle DeepMind

Computer Vision
Hawkeye: Hardware-Aware GPU Kernel Optimization with Minimal Supervision
AlphaXiv
160

Hawkeye: Hardware-Aware GPU Kernel Optimization with Minimal Supervision

Arya Tschand, Kesavan Ramakrishnan, Alexander Ingare

SPADE: Self-Play in Adaptive Synthetic Executable Environments
AlphaXiv
86

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Bo Liu, Simon Yu, Yiding Jiang

University of Washington, Stanford University, Northeastern University, Carnegie Mellon University, Massachusetts Institute of Technology

Q-Learning With World Models
AlphaXiv
77

Q-Learning With World Models

Perry Dong, Yueru Jia, Chelsea Finn

Affiliation: Stanford University, Affiliation: Peking University, Stanford University, Peking University

Machine Learning
What is Missing from AI Post-Training AI: An Empirical Analysis
AlphaXiv
60

What is Missing from AI Post-Training AI: An Empirical Analysis

Joy Jia Yin Lim, Xin Huang, Hao Peng

Affiliation: Tsinghua University, Affiliation: Renmin University of China, Tsinghua University, University of Electronic Science and Technology of China, Renmin University of China

HuggingFace Daily Papers

Robotics
τ_0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation
HuggingFace
13

τ_0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation

Xiaowei Cai, Yunuo Cai, Bingao Chen, Jingxiao Chen, Zhi Chen

Shanghai Innovation Institute

NLP
The Embedder's Dilemma: LLMs Are Better, but at What Cost?
HuggingFace
10

The Embedder's Dilemma: LLMs Are Better, but at What Cost?

Adnan El Assadi, Niklas Muennighoff, Jinhyuk Lee

Reinforcement Learning
Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses
HuggingFace
10

Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses

Tailin Zhou

HKUST

Raws Labs
TinyCast: Probabilistic Zero-Shot Forecasting with Computed Periodicity
HuggingFace
8

TinyCast: Probabilistic Zero-Shot Forecasting with Computed Periodicity

Armin Steinhauser

RAWS Labs

LeonardNJU
QuoteBench: How Matched Scores Can Hide Command-Path Failures
HuggingFace
7

QuoteBench: How Matched Scores Can Hide Command-Path Failures

Shangao Li, Yao Zhang, Volker Tresp, Yuanyuan Yang

Reinforcement Learning
FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills
HuggingFace
2

FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills

Zeyu Ren, Ling Yue, Ran Li, Yishu Wang, Shengxiang Xu

Southeast Univeristy