The Research Desk.

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

Last Brew Time: Jun 24, 2026, 7:31 AM PT

X.com Research Buzz

Reinforcement Learning
Sakana Fugu — Multi-Agent System as a Model
X.com
45295

Sakana Fugu — Multi-Agent System as a Model

Sakana AI

AlphaXiv Trending

Reinforcement Learning
Tmax: A Simple Recipe for Terminal Agents
AlphaXiv
124

Tmax: A Simple Recipe for Terminal Agents

Hamish Ivison, Junjie Oscar Yin, Rulin Shao

Unlimited OCR Works
AlphaXiv
47

Unlimited OCR Works

Youyang Yin, Huanhuan Liu, Qunyi Xie

World Action Models: A Survey
AlphaXiv
30

World Action Models: A Survey

Qiuhong Shen, Shihua Zhang, Yue Liao

National University of Singapore

NLP
ParallelKernelBench: Can LLMs Write Fast Multi-GPU Kernels?
AlphaXiv
28

ParallelKernelBench: Can LLMs Write Fast Multi-GPU Kernels?

Willy Chan, Nathan Paek, Simon Guo

Stanford University, University of California, San Diego

Reinforcement Learning
Qwen-AgentWorld: Language World Models for General Agents
AlphaXiv
25

Qwen-AgentWorld: Language World Models for General Agents

Yuxin Zuo, Zikai Xiao, Li Sheng

NLP
Tapered Language Models
AlphaXiv
24

Tapered Language Models

Universite de Montreal, Reza Bayat, Ali Behrouz, Aaron Courville

Cornell University

HuggingFace Daily Papers

NLP
LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis
HuggingFace
19

LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis

Shihao Xu, Tiancheng Zhou, Jiatong Ma, Yanli Ding, Yiming Yan

Lyncia

Computer Vision
Semantic Browsing: Controllable Diversity for Image Generation
HuggingFace
10

Semantic Browsing: Controllable Diversity for Image Generation

Sara Dorfman, Maya Vishnevsky, Omer Dahary, Or Patashnik, Daniel Cohen-Or

Retrieval
ChartWalker: Benchmarking the Cross-Chart RAG Task
HuggingFace
1

ChartWalker: Benchmarking the Cross-Chart RAG Task

Ning Tang, Chenghan Xie, Hanyang Yuan, Yi Li, Renhong Huang

Beijing Academy of Artificial Intelligence

Computer Vision
EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies
HuggingFace
1

EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies

Ganlin Yang, Zhangzheng Tu, Yuqiang Yang, Sitong Mao, Junyi Dong

shanghai ailab

NLP
QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imaging
HuggingFace
1

QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imaging

Luca Zedda, Davide Antonio Mura, Cecilia Di Ruberto, Maurizio Atzori, Muhammed Furkan Dasdelen

Reinforcement Learning
AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning
HuggingFace
0

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

Honglin Guo, Qi Zhang, Yu Zhang, Weijie Li, Rui Zheng