📄️ Contribution Guide
This section provides step-by-step guides for extending AlphaApollo with new components. Whether you want to add a new tool, plug in a new task domain, or implement a new training algorithm, these guides walk you through the full process.
📄️ Adding a New Tool
This guide walks you through extending AlphaApollo with a custom tool. By the end you will have a fully integrated tool that the LLM can invoke during multi-turn reasoning.
📄️ Adding a New Environment
This guide explains how to extend AlphaApollo with a new task environment. A new environment lets you plug a completely different problem domain (e.g. code generation, scientific reasoning, game playing) into the existing training, evolution, and testing pipelines.
📄️ Adding a New Algorithm
This guide explains how to add a new training or inference algorithm to AlphaApollo. In AlphaApollo's terminology an algorithm is surfaced as a workflow — a CLI entry point that loads a YAML config, runs data preprocessing, and launches a trainer or inference loop.