experiment: llm_directed
kind: llm_directed
seed: 1
n_replicates: 1

# Layer 2 / LLM — DIRECTED SEX (E10) in weight space: breed many recombinant offspring and keep the
# fittest. llm_moe showed fusion can COMPOSE beyond the parents (7B) but the right blend is unknown and
# base-dependent, while pure routing is capped at the best parent. Directed sex resolves both: sample a
# population of weighted merges of the specialists, score each on a held-out VALIDATION split with the
# verifier (grounding), and select the winner — reported on a fresh TEST split (no selection-on-test
# leakage). Two objectives: best-overall and best-worst-family (raw capability vs the balanced
# generalist). Prediction: directed selection beats the single a-priori soup and every parent, at
# either scale. Falsifier: directed offspring ≤ uniform soup on test.

base_model: Qwen/Qwen2.5-0.5B-Instruct   # reuses the cached llm_merge specialists
families: [lists, strings, arith]
n_train: 700          # only if cached specialists are absent
n_val: 80             # held-out split the verifier selects on
n_test: 100           # fresh split winners are reported on
n_candidates: 16      # offspring population size
concentration: 0.5    # Dirichlet concentration (<1 = sparser, specialist-dominant blends)
epochs: 3
lora: {r: 16, alpha: 32}

output: {dir: results/llm_directed}