1.
2.
Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction
(news.ycombinator.com)
3.
Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems
(news.ycombinator.com)
4.
5.
Why AI cannot do good science without humans
(feeds.nature.com)
6.
A multi-agent system for automating scientific discovery
(feeds.nature.com)
7.
8.
9.
AI swarms could hijack democracy without anyone noticing
(sciencedaily.com)
10.
Multi-Agentic Software Development Is a Distributed Systems Problem
(news.ycombinator.com)