# AI Coscientist

> Train LLMs to generate high-quality research plans via rubric-based RL without requiring experimental verification. Extracts research goals and domain-specific rubrics from scientific papers, uses frozen model as grader with 12-22% relative improvements, achieves human-expert preference 70% of time with strong cross-domain generalization.

- Skill: `adu2021/ai-coscientist` (Agent Skill)
- Install (CLI): `npx skillmds@latest add adu2021/ai-coscientist`
- Raw SKILL.md: https://api.skillmd.com/api/skills/adu2021/ai-coscientist/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- License: MIT
- Author: adu2021 (https://skillmd.com/u/adu2021)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/adu2021/ai-coscientist

---


## Overview

Automated research plan generation using extractable domain knowledge from papers.

## Core Technique

**Rubric Extraction and Grading:**

```python
# Extract from papers
research_rubrics = extract_rubrics_from_papers(papers)

# Grade via frozen model
grade = frozen_model.score(generated_plan, rubrics)

# GRPO training on grade signal
```

## When to Use

Use when: Research automation, domain-specific planning, cross-domain generalization.

## References

- Rubric extraction from scientific papers
- Frozen model as grader
- Self-reward GRPO training