2 min read

Building recursive agent systems

Source: http://x.com/i/article/2065439304785039360

At Cursor, we run thousands of agents to help us train the next version of Composer.

We give them research tasks, and if they aren't succeeding or run into issues, they DM us on Slack or page us via PagerDuty.

Scaling training for Composer

We’ve built an org chart of agents that work together.

As we’ve scaled training for

Composer, we’ve wanted to run thousands more experiments. This was possible before, but it was slow and hard to keep track of every experiment’s status. To speed things up and parallelize work, we built an always-running agent system (yes, it's a loop).

An agent system for research

Here’s how the system works:

  1. The main agent runs on a massive remote machine withall the tools you'd uselocally, plus a file on disk acting as an “inbox” for the fleet.
  2. It SSHes into machines running hundreds of child agents and collects their statuses into the inbox.
  3. On every loop, it checks fleet health, keeps healthy tasks running in the background, and surfaces anything broken to the team on Slack.
  4. Like all infra, the agents occasionally hit transient issues or need to be poked, so the main agent can control the whole fleet, quitting or restarting processes as needed.
图像

This “fleet manager” builds on our previously published research on l

ong-running agents. We’ve given the manager many different

skills that encode tacit knowledge for how to run ML experiments, review and monitor results, and more.

Researchers with superpowers

Training a great model means trying a bunch of ideas for creating useful

RL data.

A single laptop is not enough here, you really want an army of computers in the cloud to run experiments in parallel. And since we aren't

compute-constrained, we rolled out this infra for everyone in ML.

方形资料图片

Cursor @cursor_ai ·

5月18日

回复

@cursor_ai

翻译自 英语

显示原文

与 SpaceXAI 一起,我们正在从头训练一个规模大得多的模型,使用总计算量多 10 倍。 凭借 Colossus 2 的百万个 H100 等效算力和我们整合的数据与训练技术,我们预计这将是模型能力的一次重大飞跃。

89

401

4,832

[

117万

](/cursor_ai/status/2056415419536461836/analytics)

Researcher time is our scarcest resource and we’ve found a way to scale their leverage by orders of magnitude. Imagine if you had a human manager with 10,000 direct reports. Obviously that wouldn’t work well, but this human → agent “org” kind of does!

If you have a problem that is verifiable, where throwing more tokens at it will solve it faster or better, it’s worth considering building a system like this. It’s enabled us to have

swarms of agents crawling through Composer’s data to

recursively improve itself for future versions.

And if this sounds exciting,

we’re hiring!