Back to AI News
arxiv

DeepQuest: A Knowledge-Gap-Driven AI Scientist for Alzheimer's Research

Researchers introduce DeepQuest, an AI scientist framework that turns unresolved questions from Alzheimer's disease literature into traceable, testable hypotheses. It prioritizes hypotheses using data-feasibility screening and groupwise Elo ranking, then couples iterative experimentation with two-level auditing of experimental reliability and knowledge contribution. On OASIS-3, DeepQuest generated 42 feasible hypotheses and outperformed baselines in 14 of 15 evaluator-dimension comparisons across three language-model reviewers. The authors report a 95.24% audit-assessed scientific finding rate, with representative associations supported in independent ADNI and AIBL cohorts.

AI Brief

It presents a concrete research-agent framework with an auditing method and quantitative evaluation for automating traceable scientific discovery in Alzheimer's research.

arXiv:2611.26343v1 Announce Type: new Abstract: Automating experiments does not necessarily advance scientific understanding. Research agents must identify meaningful knowledge gaps, determine what available data can resolve, and assess whether their findings advance existing knowledge. We introduce DeepQuest, a knowledge-gap-driven AI scientist framework for Alzheimer's disease research. DeepQuest transforms unresolved questions from domain reviews into traceable, testable hypotheses and prioritizes them through data feasibility screening and groupwise Elo ranking. It couples iterative experimentation with two-level auditing that separates experimental reliability from knowledge contribution relative to two frozen literature corpora. On OASIS-3, DeepQuest produces 42 feasible hypotheses and outperforms the strongest baselines in 14 of 15 evaluator-dimension comparisons across three language-model reviewers. The full framework achieves an audit-assessed scientific finding rate of 95.24%, outperforming both general-purpose executors and domain-specific research agents. This scientific finding rate remains stable across literature corpora and evaluator model families. Representative findings concern neuropsychiatric symptoms and dementia risk, longitudinal amyloid spatial stability, and neocortical tau-associated clinical impairment, with key associations supported in independent ADNI and AIBL cohorts. These results show how aligning knowledge gaps, data feasibility, and evidence auditing can turn automated research into traceable, evidence-supported scientific discovery. Our source code is available at https://anonymous.4open.science/r/DeepQuest-3066/
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!