Metraipolis › archive › dc_ebd229059704

Prior or Feedback? What an LLM Uses When Adapting Neural Operators — arXiv:2610.12325

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.12325
License (as archived): CC0-1.0
Archived: 2026-10-09T05:50:38.747Z
SHA-256 of the archived text: 3b2c3a806c58ef4032fbbad2b3827bdc58d62f3166d9251dc074f0ca9cd9e22c
Stable URL of this page: https://metraipolis.com/documento/dc_ebd229059704

How to cite

Prior or Feedback? What an LLM Uses When Adapting Neural Operators — arXiv:2610.12325 — arXiv (en), https://arxiv.org/abs/2610.12325 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebd229059704 (Metraipolis archive dc_ebd229059704, sha256 3b2c3a806c58ef4032fbbad2b3827bdc58d62f3166d9251dc074f0ca9cd9e22c)

BibTeX

@misc{dcebd229059704,
  title = {Prior or Feedback? What an LLM Uses When Adapting Neural Operators — arXiv:2610.12325},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12325},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebd229059704; sha256 3b2c3a806c58ef4032fbbad2b3827bdc58d62f3166d9251dc074f0ca9cd9e22c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12325. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Do LLM scientific agents rely only on their initial task context, or do they adapt their decisions in response to experimental feedback? We study this question in neural operator adaptation, where a large language model (LLM) selects fine-tuning configurations under a limited trial budget. Across transfers within and between partial differential equation (PDE) families, the LLM achieves lower held-out test nRMSE than random search and Bayesian optimisation in nearly every matched comparison. Endpoint performance alone cannot distinguish what happens, so we verify each attribution with controlled interventions. Before observing any validation score, the LLM's first configuration already ranks near the top of the corresponding random-search pool, indicating a useful initial bias. A complementary cold-start intervention shows that the selected base learning rate shifts with the PDE description. Once feedback becomes available, reassigning validation scores among evaluated configurations changes the next proposal in every case tested, whereas a value-preserving rewrite produces no comparable aggregate effect. These interventions establish that the LLM's decision-level actions respond to the given task and observed outcomes, showing that it combines a task-dependent prior with sensitivity to experimental feedback.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Computational Physics (physics.comp-ph).
Pagina del lavoro: https://arxiv.org/abs/2610.12325 — 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 2026-10-09T05:47:01.104Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).