espl-evolutionary-system-prompt

Optimize system prompts and model weights via RL and evolutionary methods.

2|Updated Feb 12, 2026

Search Tags:#self-improvement #system-prompt #agent-performance #e-spl #evolutionary-prompt #rl-prompt-optimization #weights-learning

Ready to run

npx skills add https://github.com/hiyenwong/ai_collection --skill espl-evolutionary-system-prompt

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: espl-evolutionary-system-prompt
Source: https://github.com/hiyenwong/ai_collection/tree/main/collection/skills/espl-evolutionary-system-prompt
Command: npx skills add https://github.com/hiyenwong/ai_collection --skill espl-evolutionary-system-prompt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Dual optimization of system prompts and model weights using RL and evolutionary methods to enable agent self-improvement.

Core Features & Use Cases

Dual optimization loop combining RL updates for weights with evolutionary prompt mutations.
Genetic operators for prompts: mutation and crossover via LLM reflections.
Clear separation of declarative knowledge (prompts) and procedural knowledge (weights) to support scalable agent improvement.
Use cases include self-improving agents, multi-task optimization, and long-horizon learning tasks.

Quick Start

Initialize a population of prompts, run parallel trajectories to evaluate them, perform RL weight updates, apply prompt evolution, and iterate until convergence.

Frequently Asked Questions about espl-evolutionary-system-prompt

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

FAQPage Schema

How does co-evolving system prompts and model weights with RL improve agent performance?▼

Co-evolving system prompts and model weights with RL improves agent performance by running a dual optimization loop that applies evolutionary prompt mutations alongside reinforcement learning updates. This enables continual self-improvement for multi-task and long-horizon decision tasks.

What is the best way to optimize system prompts and model weights simultaneously?▼

The best way to optimize system prompts and model weights simultaneously is to initialize a prompt population, evaluate them via parallel trajectories, perform RL weight updates, and apply LLM reflection-based genetic mutations for prompt evolution until convergence.

Do I need an RL framework like PPO or GRPO for evolutionary prompt optimization?▼

Yes, you need an RL framework like PPO or GRPO for evolutionary prompt optimization. You also require a prompt management mechanism, a knowledge graph to store evolution history, and an LLM to perform reflection-based genetic mutations like crossover.

Can I use evolutionary prompt mutation for long-horizon learning tasks?▼

Yes, you can use evolutionary prompt mutation for long-horizon learning tasks. By maintaining a clear separation of declarative prompt knowledge and procedural weight knowledge, the system supports scalable agent improvement across complex, long-horizon environments.

Why separate declarative prompt knowledge from procedural weight knowledge in RL agents?▼

Separating declarative prompt knowledge from procedural weight knowledge in RL agents supports scalable agent improvement. It allows genetic operators to independently mutate prompts via LLM reflections while RL updates handle procedural weights, enabling robust multi-task optimization.