1.
2.
The path to artificial superintelligence
(technologyreview.com)
3.
4.
What I Learned from Reimplementing 40 Multi-Agent LLM Papers
(news.ycombinator.com)
5.
AI systems devise hypotheses and ways to test them
(feeds.nature.com)
6.
7.
8.
Building reliable agentic AI systems
(news.ycombinator.com)
9.
10.
Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction
(news.ycombinator.com)
11.
Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems
(news.ycombinator.com)
12.
13.
Why AI cannot do good science without humans
(feeds.nature.com)
14.
A multi-agent system for automating scientific discovery
(feeds.nature.com)
15.
16.
17.
Agent-harness-kit scaffolding for multi-agent workflows (MCP, provider-agnostic)
(news.ycombinator.com)
18.
19.
20.
AI swarms could hijack democracy without anyone noticing
(sciencedaily.com)
21.
Multi-Agentic Software Development Is a Distributed Systems Problem
(news.ycombinator.com)
22.
Claude Managed Agents
(news.ycombinator.com)
23.
Muse Spark: Scaling towards personal superintelligence
(news.ycombinator.com)
24.
Muse Spark: Scaling Towards Personal Superintelligence
(news.ycombinator.com)
25.
We built a multi-agent research hub. The waitlist is a reverse-CAPTCHA
(news.ycombinator.com)
26.
Agent-to-agent pair programming
(news.ycombinator.com)
27.
Agent-to-Agent Pair Programming
(news.ycombinator.com)
28.
Show HN: Sgai – Goal-driven multi-agent software dev (GOAL.md → working code)
(news.ycombinator.com)