Verified:GitHub

autoresearch

Manage autonomous AI research projects with a two-loop architecture.

Updated May 4, 2026

Search Tags:#project management #research synthesis #autonomous research #experiment orchestration #two-loop architecture

Ready to run

npx skills add https://github.com/luokai25/luo-ai-skills-market --skill autoresearch-luokai25

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: autoresearch
Source: https://github.com/luokai25/luo-ai-skills-market/tree/main/09-data-and-ai%20%28by%20Luo%20Kai%29/10-research-analysis/0-autoresearch-skill
Command: npx skills add https://github.com/luokai25/luo-ai-skills-market --skill autoresearch-luokai25

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires exa_mcp, semanticscholar, arxiv, crossref, 21-research-ideation, ml-paper-writing, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill solves the problem of managing complex, autonomous AI research projects with a two-loop architecture, allowing for efficient experiment orchestration and synthesis.

Core Features & Use Cases

Two-Loop Architecture: Manages rapid experiment iterations and synthesizes results for continuous improvement.
Experiment Orchestration: Routes to domain-specific skills for execution, supports continuous agent operation.
Research Synthesis: Identifies patterns and steers research direction, producing research presentations and papers.
Use Case: Ideal for starting research projects, running autonomous experiments, or managing multi-hypothesis research efforts.

Quick Start

Set up your workspace structure. Use the autoresearch skill to initiate your project by defining your research question, selecting hypotheses, and setting up your initial research workspace.

Frequently Asked Questions about autoresearch

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I manage autonomous AI research projects from literature survey to published paper?▼

To manage autonomous AI research projects, use a two-loop architecture that handles the full research lifecycle. It orchestrates rapid experiment iterations, synthesizes results, and steers research direction from initial literature search to final paper publication.

What is the two-loop architecture for autonomous research and experiment orchestration?▼

The two-loop architecture is a management mechanism for autonomous research. One loop drives rapid experiment iterations and execution, while the second loop synthesizes results and identifies patterns to continuously steer the research direction.

How do I set up a workspace for autonomous experiment orchestration and multiple hypothesis testing?▼

Set up your workspace by defining a research question and selecting initial hypotheses. The system then initiates the project, routing domain-specific skill execution and tracking experiments to support continuous agent operation.

Do I need external search tools to run literature surveys for autonomous research synthesis?▼

Yes, autonomous research synthesis requires external search tools. The system depends on integrations like exa_mcp, arxiv, semanticscholar, and crossref to conduct literature surveys and gather necessary research data for hypothesis formation.

Can I use this system for continuous agent operation across multi-hypothesis research efforts?▼

Yes, the system supports continuous agent operation for multi-hypothesis research efforts. It routes tasks to domain-specific skills for execution, allowing agents to run continuously while tracking and synthesizing multiple experiments.

What are the limitations of using a two-loop architecture for autonomous AI research?▼

The two-loop architecture requires predefined workspace setup and external dependencies for literature search. It is limited by the need for continuous agent operation and relies on domain-specific skill routing to execute complex experiments.