The Research Desk.

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

Last Brew Time: Apr 23, 2026, 9:42 AM PT

X.com Research Buzz

Reinforcement Learning
Agents of Chaos
X.com
3461

Agents of Chaos

Natalie Shapira, Chris Wendler, Avery Yen, Gabriele Sarti, Koyena Pal, Olivia Floody, Adam Belfki, Alex Loftus, Aditya Ratan Jannali, Nikhil Prakash, Jasmine Cui, Giordano Rogers, Jannik Brinkmann, Can Rager, Amir Zur, Michael Ripa, Aruna Sankaranarayanan, David Atkinson, Rohit Gandikota, Jaden Fiotto-Kaufman, EunJeong Hwang, Hadas Orgad, P Sam Sahil, Negev Taglicht, Tomer Shabtay, Atai Ambus, Nitay Alon, Shiri Oron, Ayelet Gordon-Tapiero, Yotam Kaplan, Vered Shwartz, Tamar Rott Shaham, Christoph Riedl, Reuth Mirsky, Maarten Sap, David Manheim, Tomer Ullman, David Bau

Reinforcement Learning
AI Agent Traps
X.com
2080

AI Agent Traps

Matija Franklin, Nenad Tomašev, Julian Jacobs, Joel Z. Leibo, Simon Osindero

AlphaXiv Trending

Qwen3.5-Omni Technical Report
AlphaXiv
132

Qwen3.5-Omni Technical Report

Qwen Team

Reinforcement Learning
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
AlphaXiv
112

Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence

Guanting Dong, Junting Lu, Junjie Huang

Reinforcement Learning
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
AlphaXiv
90

Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems

Jiacheng Liu, Xiaohan Zhao, Xinyi Shang

Computer Vision
OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
AlphaXiv
45

OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Jinghui Lu, Jiayi Guan, Zhijian Huang

Neural Garbage Collection: Learning to Forget while Learning to Reason
AlphaXiv
40

Neural Garbage Collection: Learning to Forget while Learning to Reason

Michael Y. Li, Jubayer Ibn Hamid, Emily B. Fox

Computer Vision
Image Generators are Generalist Vision Learners
AlphaXiv
37

Image Generators are Generalist Vision Learners

Valentin Gabeur, Shangbang Long, Songyou Peng

HuggingFace Daily Papers

Reinforcement Learning
OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
HuggingFace
19

OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis

Kanzhi Cheng, Zehao Li, Zheng Ma, Nuo Chen, Jialin Cao

Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL
HuggingFace
2

Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL

Skylar Zhai, Jingcheng Liang, Dongyeop Kang

Computer Vision
Image Generators are Generalist Vision Learners
HuggingFace
2

Image Generators are Generalist Vision Learners

Valentin Gabeur, Shangbang Long, Songyou Peng, Paul Voigtlaender, Shuyang Sun

Efficiency
Streaming Structured Inference with Flash-SemiCRF
HuggingFace
1

Streaming Structured Inference with Flash-SemiCRF

Benjamin K. Johnson, Thomas Goralski, Ayush Semwal, Hui Shen, H. Josh Jang

COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
HuggingFace
0

COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling

Noah Flynn

Machine Learning
Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs
HuggingFace
0

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs

Jaechul Roh, Amir Houmansadr