analiza aiqbench
This arXiv preprint presents an LLM-based framework that builds and revises scientific principles during discovery tasks, evaluated on molecular optimization, protein engineering, gene perturbation, and property prediction. The reported gains are over baselines that rely on internal knowledge, external sources, or experience summaries, but the abstract gives no effect sizes or comparison details, so the practical lift is unclear until the full results are checked. For readers, the main point is the approach of letting an LLM generate and refine hypotheses at test time, which bears on whether language models can meaningfully support scientific workflows.
Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery
arXiv:2610.32195v1 Announce Type: new Abstract: 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.
Abstract: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.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2610.32195 [cs.LG]
(or arXiv:2610.32195v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.32195 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 311 cuvinte
Subiecte conexe
Actively Resolving Contextual Uncertainty for Underspecified Tasks in Natural Language
arXiv · 28 sept. 2026
Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and Theories
arXiv · 5 oct. 2026
EVAR: Evidence-Validated Hypothesis Admission for Budget-Aware Narrative Reasoning
arXiv · 1 sept. 2026
AdaPLD: Adaptive Retrieval and Reuse for Efficient Model-Free Speculative Decoding
arXiv · 17 iun. 2026