Alexander N. Daryin

Alexander N. Daryin

Auto-generated profile, based on publicly available information

Alexander N. Daryin

Lomonosov Moscow State University

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 May 2026 in Nature
Verified
Journal Article
Open access
JGJuraj Gottweis
Juraj Gottweis
WWWei-Hung Weng
Wei-Hung Weng
ADAlexander Daryin
Alexander Daryin
TTTao Tu
Tao Tu
PSPetar Sirkovic
Petar Sirkovic
VNVivek Natarajan
Vivek Natarajan
Scientific discovery is driven by scientists generating hypotheses for complex problems that undergo rigorous experimental validation. To augment this process, we introduce Co-Scientist, a multi-agent artificial intelligence (AI) system built on Gemini for structured scientific thinking and hypothesis generation. Co-Scientist aims to help scientists discover new original knowledge. Conditioned on their research objectives and previous scientific evidence, it formulates demonstrably novel research hypotheses for experimental verification. The system’s design involves agents continuously generating, critiquing and refining hypotheses accelerated by scaling test-time compute. Key contributions include (1) a multi-agent architecture with an asynchronous task execution framework for flexible compute scaling, and (2) a tournament evolution process for self-improving hypotheses generation. Automated evaluations show continued benefits of test-time compute scaling, improving hypothesis quality over time. Although this is a general-purpose system, we focus the validation in three biomedical applications: drug repurposing; novel-target discovery 1 ; and explaining mechanisms of antimicrobial resistance 2 . Specifically, Co-Scientist helped to identify new drug-repurposing candidates and synergistic combination therapies for acute myeloid leukaemia that were validated through in vitro experiments. These real-world validations demonstrate the potential of Co-Scientist to accelerate scientific discovery and usher in an era of AI-empowered scientists.

31 December 2008 in Annual Reviews in Control
Verified
Journal Article
Closed access
AKA.B. Kurzhanski
A.B. Kurzhanski
ADA.N. Daryin
A.N. Daryin

1 January 2006
Verified
Conference Paper
Closed access
ADA. N. Daryin
A. N. Daryin
AKA. B. Kurzhanski
A. B. Kurzhanski
IVI. V. Vostrikov
I. V. Vostrikov
This paper indicates effective solution schemes for problems of closed-loop control for oscillating systems of high dimensions subjected to unknown but bounded disturbances. These schemes are based on using internal ellipsoidal approximations of weakly invariant solvability sets and produce effective numerical algorithms. The text is accompanied by computer animation and numerical simulations based on ellipsoidal tools for calculating reach sets

1 January 2020
Verified
Book
Closed access
AKAlexander B. Kurzhanski
Alexander B. Kurzhanski
ADAlexander N. Daryin
Alexander N. Daryin

1 January 2013 in Computational Mathematics and Mathematical Physics
Verified
Journal Article
Closed access
PDF file
ADA. N. Daryin
A. N. Daryin
AKA. B. Kurzhanski
A. B. Kurzhanski
The development of efficient computational methods for synthesizing controls of high-dimensional linear systems is an important problem in theoretical mathematics and its applications. This is...

1 December 2012
Verified
Conference Paper
Closed access
ADAlexander N. Daryin
Alexander N. Daryin
AKAlexander B. Kurzhanski
Alexander B. Kurzhanski
The estimation of reachability sets for systems of high dimensions is a challenging issue due to its high computational complexity. For linear systems, an efficient way of calculating such estimates is to find their set-valued approximations provided by ellipsoidal calculus. The present paper deals with various aspects of such approach as applied to systems of high dimensions with unknown but bounded input disturbances. We present an innovative technique based on parallel computation that involves on-line mixing of ellipsoidal tubes found in parallel. This improves robustness of the ellipsoidal estimates. Finally discussed is an implementation of the algorithm intended for supercomputer clusters.