Constructing Reflective Immediate Optimization with GEPA: Multi-Element Prompts, Structured Suggestions, and Held-Out Validation
def make_problems(n, seed=0): rng = random.Random(seed) out = [] for _ in vary(n): t = rng.selection([“discount”, “travel”, “wallet”, “chain”]) if t == “low cost”: unit = rng.selection([40, 60, 80, 120]) qty = rng.selection([5, 6, 8, 10]) disc = rng.selection([10, 20, 25, 50]) complete = unit * qty gold = complete – complete * disc //…