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.

설치로 이동

저장소: ADu2021/skillXiv
최근 소스 활동: 2026년 3월 24일 19:42
감지된 SKILL.md 언어: 영어
스타: 6
포크: 0

설치 방법

기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.

npx skills add https://github.com/ADu2021/skillXiv --skill ai-coscientist

명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.

로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.

소스 파일 검토

설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.

SKILL.md

소스 지침 · 읽기 전용 미리보기

검색으로 돌아가기 설치로 돌아가기

meaningful-kebab-case-name

Convert arXiv papers into ready-to-use agent skills using category-aware extraction. First classifies the paper into one or more of 11 research categories, then applies a specialized extraction pipeline for each category — because different types of papers produce different types of usable knowledge. A single paper can yield multiple skills if it spans categories. Use this skill whenever the user wants to turn a paper into a skill, extract practical techniques from research, build a skill library from papers, convert arXiv papers into reusable agent instructions, or batch-process multiple papers into skills. Also trigger when someone asks about extracting actionable knowledge from papers, making research practical for LLM agents, or systematically converting academic contributions into structured agent capabilities.

2026-03-26

action-quantization-behavior-cloning

Establish regret bounds for behavior cloning with discretized actions combining statistical error and quantization error terms. Prove smoothness requirements for safe quantizer design, show that learning-based quantizers fail these requirements, and propose model-based augmentation to reduce error dependence from H² to H.

2026-03-26

adaptive-lora-personalized-ranks

Dynamically allocate LoRA ranks per-layer during fine-tuning instead of using fixed uniform ranks. Learn optimal rank for each layer and subject via variational framework with discretized exponential distribution, reducing memory footprint while maintaining fidelity and text-alignment.

2026-03-26

이 저장소의 모든 Skills 보기

name	ai-coscientist
title	Training AI Co-Scientists Using Rubric Rewards
version	0.0.2
engine	skillxiv-v0.0.2-claude-opus-4.6
license	MIT
url	https://arxiv.org/abs/2512.23707
keywords	["research","reinforcement-learning","rubric-rewards","cross-domain"]
description	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.

Overview

Automated research plan generation using extractable domain knowledge from papers.

Core Technique

Rubric Extraction and Grading:

# 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

ai-coscientist

소스 정보

설치 방법

소스 파일 검토

이 저장소의 다른 Skills

이 저장소의 다른 Skills

Overview

Core Technique

When to Use

References

Overview

Core Technique

When to Use

References