aris-autonomous-ml-research

---
name: aris-autonomous-ml-research
description: Autonomous ML research workflows using ARIS (Auto-Research-In-Sleep) — Markdown-only skills for cross-model paper review, idea discovery, experiment automation, and paper writing with Claude Code, Codex, or any LLM agent.
triggers:
  - "set up ARIS for autonomous research"
  - "run research pipeline while I sleep"
  - "automate ML paper writing with Claude Code"
  - "cross-model review loop for my paper"
  - "use ARIS to find research ideas"
  - "run experiment automation with ARIS"
  - "set up auto paper review workflow"
  - "write rebuttal with ARIS"
---

# ARIS — Auto-Research-In-Sleep

> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection.

ARIS is a **zero-dependency, Markdown-only** autonomous ML research system. Every "skill" is a plain `SKILL.md` file that any LLM agent can read and execute. It orchestrates cross-model collaboration — one model executes research (Claude Code, Codex, etc.) while another acts as adversarial reviewer (GPT-5.4, Gemini, GLM, MiniMax, etc.) to break self-play blind spots.