meta-learning-evolution

Name: meta-learning-evolution
Availability: InStock
Author: kangoxford

Automate meta-learning pipeline design by evolving code, prompts, and configurations.

1|Updated Apr 23, 2026

Search Tags:#llm #evolution #meta-learning #prompt-design #genetic-algorithm #experiment-structure

Ready to run

npx skills add https://github.com/KangOxford/auto-quant-research --skill meta-learning-evolution

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: meta-learning-evolution
Source: https://github.com/KangOxford/auto-quant-research/tree/main/execution-layer/skills/meta-learning-evolution
Command: npx skills add https://github.com/KangOxford/auto-quant-research --skill meta-learning-evolution

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Design meta-learning systems that automatically evolve code, configurations, and prompts using genetic algorithms and large language models, enabling faster discovery and automation of outer-loop optimization workflows.

Core Features & Use Cases

Level-1 GA-guided evolution for outer-loop optimization of loss functions, rewards, and hyperparameters.
Level-2 LLM-driven prompt and primitive discovery to supplement GA search and inject new capabilities when stagnation occurs.
A two-level evolution workflow with explicit evaluation metrics, reproducible experiment templates, and guidance for when to apply GA vs LLM.

Quick Start

Provide a two-level evolution plan that uses a genetic algorithm for outer-loop optimization and an LLM to invent new primitives when stagnation occurs, with explicit prompts and evaluation metrics.

Frequently Asked Questions about meta-learning-evolution

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

FAQPage Schema

How do I automate meta-learning pipeline design with genetic algorithms and LLMs?▼

To automate meta-learning pipeline design, you evolve code, prompts, and configurations using a two-level workflow where a genetic algorithm handles outer-loop optimization and an LLM invents new primitives when search stagnates. This requires a deterministic evaluation harness and experiment templates.

What is the best way to evolve loss functions and hyperparameters automatically?▼

The best way to evolve loss functions and hyperparameters automatically is using Level-1 GA-guided evolution for outer-loop optimization. This approach systematically explores and mutates configurations to discover optimal parameters across GA and LLM-driven workflows.

When should I use LLM-driven prompt discovery instead of genetic algorithms?▼

You should use LLM-driven prompt discovery instead of genetic algorithms when your GA search stagnates. Level-2 LLM-driven evolution supplements GA search by injecting new capabilities and inventing new primitives to unblock the optimization process.

Do I need a deterministic evaluation harness to set up two-level evolution workflows?▼

Yes, you need a deterministic evaluation harness to set up two-level evolution workflows. A deterministic harness ensures reproducible experiment templates, providing explicit evaluation metrics to reliably measure the performance of evolved prompts, code, and configurations.

Can I use this approach to optimize reward functions for automated development tasks?▼

Yes, you can use this approach to optimize reward functions for automated development tasks. The workflow applies to research and development tasks involving the automated exploration of loss functions, rewards, and hyperparameters across GA and LLM-driven workflows.

What are the limitations of using GA for outer-loop optimization in meta-learning?▼

A key limitation of using GA for outer-loop optimization in meta-learning is search stagnation, where the algorithm stops finding improved loss functions or hyperparameters. This requires supplementing the GA search with LLM-driven prompt and primitive discovery to inject new capabilities.