←
Outerloop10 posts
Outerloop avatar

Outerloop

@outerloop_sci

Open autoresearch agents | outerloop.science

◷ Joined September 2026▧ 4 Photos and videos
NYU Center for Data Science avatar
⟳ Outerloop retweeted
NYU Center for Data Science@NYUDataScience·Nov 11

CDS Asst. Prof. Mengye Ren (@mengyer) and his lab released @outerloop_sci, open-source software whose AI agents open pull requests only when their experiments improve a benchmark. The agents got a GPT model to its target in 77% fewer training steps. outerloop.science/

Outerloop avatar
Outerloop@outerloop_sci·Nov 1

On a nanoGPT training-speed benchmark, we reran three published systems on new seeds. Their gains shrank due to lucky seeds. With the same coding model, the systems reach similar scores. What's different is whether you can trust the reported numbers.

Post attachment
Outerloop avatar
Outerloop@outerloop_sci·Nov 1

New paper: Outerloop: Open and Trustworthy Multi-Agent Autoresearch. In most open autoresearch systems, the agent grades its own results. Outerloop is a kernel that runs agents as untrusted programs and keeps measurement and review outside their sandboxes.

Post attachment
Outerloop avatar
Outerloop@outerloop_sci·Oct 27

Outerloop 0.6.0 is out. It now runs locally on a Mac, can use a local git forge instead of GitHub, and keeps a hash-chained, attested record of each agent run. Run "outerloop trajectory <run-id> --verify" to check one.

Outerloop avatar
Outerloop@outerloop_sci·Oct 5

Outerloop 0.3.0 is out: run autoresearch agents fully on your own hardware. Here, Claude Code and Codex authors run on a self-hosted GLM-5.3. pip install outerloop-science==0.3.0

Post attachment
Outerloop avatar
Outerloop@outerloop_sci·Sep 18

Outerloop 0.2.0 is out. A lifecycle release: research agents now have persistent states instead of running once and exiting, and one unified message inbox: agent-to-agent messages, kernel notices, gate verdicts, reviewer findings, branch moves and CI results.

Outerloop avatar
Outerloop@outerloop_sci·Sep 10

Outerloop 0.1.0 is out. A fleet of AI agents that improve your benchmarks on your code. Agents propose changes, run them on your cluster, and open pull requests when the metrics improve. We are open source. Let's embrace open science! Get started at outerloop.science