Symbolic Equation

This implements LLM-SR, an evolutionary algorithm where Claude proposes equation mutations instead of random ones. You feed it data with variable names and physical context, and it runs a multi-island search where each island clusters equations by performance, samples top candidates via softmax, and asks the LLM to improve them in versioned prompts. Islands reset periodically to maintain diversity. It's designed for symbolic regression when you want interpretable scientific equations, not just black box fits. The evolutionary loop is clever, using temperature scheduling and Occam's razor within clusters, but you'll need decent computational budget since it evaluates many candidate equations with parameter optimization.