Metraipolis › archive › dc_e641b8be0012
A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization — arXiv:2608.08156
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.08156
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:15:03.179Z
- SHA-256 of the archived text
4d43f4df88e6b52ae0cc4b7418efd9d0f7003d24a941eba3f688ac64a1645fca- Stable URL of this page
https://metraipolis.com/documento/dc_e641b8be0012
How to cite
A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization — arXiv:2608.08156 — arXiv (en), https://arxiv.org/abs/2608.08156 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e641b8be0012 (Metraipolis archive dc_e641b8be0012, sha256 4d43f4df88e6b52ae0cc4b7418efd9d0f7003d24a941eba3f688ac64a1645fca)
BibTeX
@misc{dce641b8be0012,
title = {A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization — arXiv:2608.08156},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.08156},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e641b8be0012; sha256 4d43f4df88e6b52ae0cc4b7418efd9d0f7003d24a941eba3f688ac64a1645fca},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08156. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In evolutionary algorithms powered by language models, the LLM acts as a single operator that simultaneously updates structural components (like control flow) and continuous parameters. While LLMs can be good at the first, they are not efficient at the second, wasting tokens taking discrete jumps inside a trial and error loop. We resolve this by formalizing a hybrid nested search, in which an outer loop has the LLM propose a structural sketch, with numeric gaps, and an inner numerical optimizer tunes the sketch. Both the outer and inner solvers are pluggable: any text-based optimizer can be combined with a zero-order optimizer (CMA-ES), gradient-based routines, or MCMC samplers. We validate our framework across three scientific domains: (i) meta-optimizers on closed-form test functions, (ii) code-based policies for systems research and social dilemmas; and (iii) approximate Bayesian inference tasks. Across all three, the hybrid optimizer is superior to both vanilla LLM-driven search and pure numerical optimization baselines. Code at: this https URL Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.NE). Categorie arXiv: Machine Learning (cs.LG) ; Neural and Evolutionary Computing (cs.NE). Pagina del lavoro: https://arxiv.org/abs/2608.08156 — 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 2026-10-19T09:12:57.246Z dalla pagina https://arxiv.org/catchup/cs.NE/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).