Metraipolis › archive › dc_3ca9601097ea

Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery — arXiv:2610.32195

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.32195
License (as archived): CC0-1.0
Archived: 2026-10-26T19:51:46.947Z
SHA-256 of the archived text: 2e9fdf2decc27c5a20d1f1d687dc6827bb607509d6d66906f45043debee71a18
Stable URL of this page: https://metraipolis.com/documento/dc_3ca9601097ea

How to cite

Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery — arXiv:2610.32195 — arXiv (en), https://arxiv.org/abs/2610.32195 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ca9601097ea (Metraipolis archive dc_3ca9601097ea, sha256 2e9fdf2decc27c5a20d1f1d687dc6827bb607509d6d66906f45043debee71a18)

BibTeX

@misc{dc3ca9601097ea,
  title = {Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery — arXiv:2610.32195},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32195},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ca9601097ea; sha256 2e9fdf2decc27c5a20d1f1d687dc6827bb607509d6d66906f45043debee71a18},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32195. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scientific discovery requires identifying the scientific principles underlying observed phenomena to guide further investigation. As these empirical principles are often unknown in complex discovery processes, they are constructed via a hypotheses-to-principle pipeline to obtain recurring causalities from progressively accumulated observations during test-time discovery. However, constructing this knowledge requires substantial domain expertise, time, and effort, making this translation stage a bottleneck for scientific discovery. To address this limitation, we propose Principia, an LLM-based framework that constructs and continually refines scientific principles at test time. Drawing on how human researchers develop principles, Principia forms comparative causal hypotheses from related inputs and their observed outcomes, then synthesizes recurring relationships across these hypotheses into inductive principles. By applying the constructed hypotheses and inductive principles to the task, it obtains new observations, revises the hypotheses used based on these new observations, and reconstructs principles from the updated hypotheses, allowing scientific knowledge to continuously evolve throughout test-time discovery. Across benchmarks spanning molecular optimization, protein engineering, gene perturbation, and molecular property prediction, Principia outperforms baselines relying on internal knowledge, external sources, or experience summaries, while generating principles that are plausible and consistent with the scientific literature, demonstrating its effectiveness in constructing and refining task-specific hypotheses and principles at test time for scientific discovery. Our code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.32195 — 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 2026-10-26T19:45:33.396Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).