AetherLabsAI/RSIAgent
A training-free multi-agent framework for recursive self-improvement in new environments through broad-then-deep autonomous exploration and reusable memory.
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
<img src="https://img.shields.io/badge/Companion-RSIGame-FF7A45?style=flat&logo=github&logoColor=white" News · Demos · Method · Results · Quickstart · Documentation · Citation https://github.com/user-attachments/assets/11cb3919-1073-4ba3-8bcd-37a15ec53c33 RSIAgent is a training-free framework for recursive self-improvement in new digital environments. It coordinates the Curriculum Agent, Actor Agent, and Verifier Agent to discover how an environment works, check what they learn against actual execution, and retain reusable knowledge in persistent memory. Model parameters stay fixed throughout exploration and downstream task execution. The paper's central strategy is broad-then-deep exploration: first acquire diverse experience, then investigate hard cases, hidden constraints, and boundary conditions. The resulting memory contains procedures, scripts, and failure lessons that the Actor Agent reuses for downstream task execution. https://github.com/user-attachments/assets/b939a9c2-4acb-4c30-b72e-18bab646529c [](docs/assets/framework.png) The paper's original framework figure, illustrated with a FreeCAD task. Broad experience is progressively refined into targeted memory, then frozen for reuse. Click the figure for full resolution. Figure provenance. Three agents carry out the recursive learning loop: accumulated knowledge, then decides…
Read the full README ↗ · Preview checked 2026-10-30T09:36:34.487Z
Inside the original README — Document outline
- 📰 News & Highlights
- 🧭 Overview
- 🎬 Demos
- 🧩 Framework
- 🔄 Method
- 📊 Results
- 🧪 Benchmarks
- 🗂️ Repository layout
- ⚙️ Installation
- 🖥️ OSWorld
- 🎓 ALE
- 🚀 Run batches
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
A training-free multi-agent framework for recursive self-improvement in new environments through broad-then-deep autonomous exploration and reusable memory.
Repository facts
- Owner
- AetherLabsAI
- Primary language
- Python
- Stars
- 358
- Forks
- 40
- Open issues + pull requests
- 8
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-09-13T01:48:25.000Z
- Last push
- 2026-09-16T04:05:23.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-09-20T06:40:45.138Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer