Metraipolis › archive › dc_c56cb43dbedd

Lineage Is Memory: Parent Inheritance and Feedback Disclosure in Short-Budget LLM-Guided Optimization — arXiv:2610.41157

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41157
License (as archived)
CC0-1.0
Archived
2026-11-03T07:22:26.006Z
SHA-256 of the archived text
6e0f01c6eb405f84eee07e8fdc65de4207a0330c1d09388f1d5bda1e6f2b542a
Stable URL of this page
https://metraipolis.com/documento/dc_c56cb43dbedd

How to cite

Lineage Is Memory: Parent Inheritance and Feedback Disclosure in Short-Budget LLM-Guided Optimization — arXiv:2610.41157 — arXiv (en), https://arxiv.org/abs/2610.41157 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c56cb43dbedd (Metraipolis archive dc_c56cb43dbedd, sha256 6e0f01c6eb405f84eee07e8fdc65de4207a0330c1d09388f1d5bda1e6f2b542a)
BibTeX
@misc{dcc56cb43dbedd,
  title = {Lineage Is Memory: Parent Inheritance and Feedback Disclosure in Short-Budget LLM-Guided Optimization — arXiv:2610.41157},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41157},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c56cb43dbedd; sha256 6e0f01c6eb405f84eee07e8fdc65de4207a0330c1d09388f1d5bda1e6f2b542a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41157. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Iterative language-model optimizers refine prompts and programs by evaluating a candidate, showing a proposer model a sample of failing cases, and keeping revisions that improve performance. Recent work attributes the limits of this loop to narrow single-round reflection, introducing full-set error clustering, targeted minibatches, or larger proposer models so the optimizer sees more failure modes per step. Yet every existing evaluation tests these mechanisms exclusively inside lineage-preserving search, where each revision edits a surviving parent, leaving the contribution of parent inheritance confounded with the breadth of per-round feedback. Across 1,750 pre-registered runs spanning nine prompt and program synthesis benchmarks, we separate parent inheritance from feedback disclosure under matched evaluation budgets. We find that greedy parent inheritance drives the vast majority of optimization progress, outperforming seed-reset resampling even when seed-reset proposals receive a clustered summary of all failures in every round or use a larger proposer model. While full-set error clustering and diverse failure selection improve single-step rewrites from the seed and accelerate the opening rounds of search, sequential parent inheritance rapidly closes this gap as solved error modes are retained in the candidate and filtered from subsequent failure lists. Moreover, decomposing token expenditure in GEPA reveals that proposer reflection accounts for only a small fraction of total cost whereas validation and minibatch gating consume nearly the entire budget, showing that greedy parent inheritance over raw failures captures the gains of complex reflective loops at a fraction of their compute.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.41157 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T07:19:48.894Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).