Metraipolis › archive › dc_c41198ded7ce
FGSS-BO: Feedback-Guided Hypothesis Management for LLM-Based Bayesian Optimization — arXiv:2610.21246
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21246
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:55:54.574Z
- SHA-256 of the archived text
ffd4dde276ff00085ea3e209915f32bc04b1753dae1ce7b21628bd07fc4e5397- Stable URL of this page
https://metraipolis.com/documento/dc_c41198ded7ce
How to cite
FGSS-BO: Feedback-Guided Hypothesis Management for LLM-Based Bayesian Optimization — arXiv:2610.21246 — arXiv (en), https://arxiv.org/abs/2610.21246 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c41198ded7ce (Metraipolis archive dc_c41198ded7ce, sha256 ffd4dde276ff00085ea3e209915f32bc04b1753dae1ce7b21628bd07fc4e5397)
BibTeX
@misc{dcc41198ded7ce,
title = {FGSS-BO: Feedback-Guided Hypothesis Management for LLM-Based Bayesian Optimization — arXiv:2610.21246},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21246},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c41198ded7ce; sha256 ffd4dde276ff00085ea3e209915f32bc04b1753dae1ce7b21628bd07fc4e5397},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21246. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model (LLM)-guided Bayesian optimization (BO) uses past observations to guide search, but proposed directions and their revision can remain implicit. We propose Feedback-Guided Search State (FGSS), a structured hypothesis-management interface connecting language-based guidance to observed evidence, executable parameter interventions, and comparative support updates. An LLM reflector proposes and revises hypotheses; a deterministic curator validates them and maintains identities and test records. The evolving state guides candidate construction and priorities. Instantiated on LLAMBO, FGSS-BO retains its surrogate and default expected improvement selection, with a bounded testing policy. On two retrospective protocol/media tasks with nearest-neighbor response oracles, it attains higher sample mean final best and search AUC than the matched LLAMBO baseline and evaluated non-LLM baselines. Prose-reflection and EI-only controls show mixed component effects. Six direct-training hyperparameter-optimization tasks show task-dependent transfer, strongest on diabetes SVM; exact-grid and reaction controls examine other settings. FGSS exposes hypotheses, their execution, and cross-round revisions for inspection while supporting search gains in selected settings. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.21246 — 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 2026-10-16T08:44:47.633Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).