Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

HKUST open-sources The Fourth Institute, an agent-society automated research platform

AI summary

According to Xinzhiyuan, a team led by HKUST professors Zheng Guangting and Ma Songchen has open-sourced on GitHub an automated research platform called The Fourth Institute, where human researchers collaborate with AI agents through roles such as Resident, Lineage and Family, coordinated by the HATG ISA multi-agent specification and execution traces. The team says the platform has accumulated over 1.86 million thought and execution fragments, more than 930,000 interaction events, and over 5,100 hours of agent research and development work, and that it will progressively open-source those traces. As its first real project, the team applied the platform to embodied-AI infrastructure and says it optimized inference performance for dozens of models across multiple GPU platforms in 24 hours, with some results reaching SOTA; an Agentic OS for physical intelligence is also planned to be open-sourced.

In-depth insight

The project packages long-running multi-agent research collaboration, previously accessible mainly to top labs, as an open-source platform that individual researchers can join, and offers reusable conventions for humans and agents sharing knowledge, memory and work traces.

新智元 2026-10-20 12:38 北京

新智元报道  

「全球只有大约5,000人,真正见识过顶尖AI的能力。」这是Andrej Karpathy近日分享的一个观察。他说,只有站在漏斗顶端的那一小撮研究者,才能看到数千个AI Agent长时间协作、昼夜不停地做科研。

换句话说:Agent集群正在改写科研的玩法,但这场游戏,目前只有极少数人拿到了入场券。

智能体重塑科研,这已经是不可逆的潮流。可绝大多数研究者——不是大厂,不是头部实验室,就是一个普通人带着几张GPU卡和几个模型账号——该怎么参与进来?

#The Fourth Institute#Hong Kong University of Science and Technology#Codex#Claude Code#Meta Muse#OpenAI dots

Original · 11 min readRead the original
Group chat

No comments yet. Start the conversation.