Principia:測試時假設轉化為原理,推動科學發現
Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery
Principia 是一個基於 LLM 的框架,可在推理期間建構並反覆修訂科學原理,以推動分子及生物任務的科學發現。它從相關輸入及觀察結果形成因果假設,再歸納反覆出現的關係為原理,並根據新觀察持續更新假設與原理。在涵蓋分子最佳化、蛋白質工程、基因擾動及分子性質預測的基準測試中,Principia 表現優於依賴內部知識、外部來源或經驗摘要的基線。
Published on Oct 23
Authors:
,
,
,
Abstract
Principia is an LLM-based framework that builds and iteratively refines scientific principles during inference to accelerate discovery across molecular and biological tasks.
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 https://github.com/DongkiKim95/Principia.
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2610.32195
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.32195 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.32195 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.32195 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co