Lineage Is Memory: Parent Inheritance and Feedback Disclosure in Short-Budget LLM-Guided Optimization
Read the original on arXiv Computation and Language →The paper investigates how iterative language‑model optimizers improve prompts and programs by evaluating candidates, exposing failing cases to a proposer model, and retaining revisions that enhance performance. By conducting 1,750 pre‑registered experiments across nine benchmarks, the authors disentangle the effects of parent inheritance (keeping a surviving parent) from feedback disclosure (providing failure summaries) under equal computational budgets. They find that greedy parent inheritance alone drives most optimization gains, outperforming seed‑reset strategies even when the latter receive comprehensive failure summaries or larger proposer models, and that the cost of proposer reflection is minimal compared to validation and minibatch gating.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.