How RecursiveMAS speeds up multi-agent inference by 2.4x and reduces token usage by 75%

UIUC and Stanford's RecursiveMAS lets AI agents collaborate in embedding space instead of text, cutting token usage by 75% and speeding inference 2.4x.
The Hacker News

ThreatsDay Bulletin: Claude Security Plugin, Azure Priv-Esc, Kali365 MFA Bypass, FIFA Scams +15 More

Massive regional C2 footprint More than 1.3K C2 Servers Discovered in the Middle East Hunt.io said it identified more than ...
Nature

Move over, AlphaFold: open-source model predicts shape of 1 billion proteins

The new open-source atlas, generated by an AI tool called ESMFold2, vastly increases the known protein universe.
IEEE

A Federal Recursive RUL Prediction Approach for Inter-Client Information Complementarity for Missing Data

Abstract: RUL (Remaining useful life, RUL) prediction is one of the most important methods to ensure the safe operation of mechanical equipment. When continuous time segments are missing from the ...