Alexander N. Daryin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Alexander N. Daryin has a total of 71 co-authors. Here are the top co-authors by number of shared publications:
Alexander B. Kurzhanski
6 shared publicationsA. B. Kurzhanski
Moscow State University
4 shared publicationsA.B. Kurzhanski
Moscow State (Lomonosov) University Faculty of Computational Mathematics and Cybernetics
4 shared publications- A. A. Mel'Nikova
Lomonosov Moscow State University
2 shared publications - Alexander B. Kurzhanski
Lomonosov Moscow State University
2 shared publications I. A. Digailova
Moscow State University
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 19 May 2026
- Published by Springer Nature in Nature
- Vol. 655 (8122) , 487-496
Accelerating scientific discovery with Co-Scientist
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.
- 19 May 2026
- Published by Springer Nature in Nature
- Vol. 655 (8122) , 487-496
Top Cited PapersOpen AccessAccelerating scientific discovery with Co-Scientist
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.
- 15 November 2024
- Published by The Russian Academy of Sciences in Дифференциальные уравнения
- Vol. 60 (11) , 1484-1498
ON THE PROPERTIES OF THE SOLVABILITY SET FOR A LINEAR SYSTEM WITH UNCERTAINTY
The work is devoted to the problem of verifying that the state of a linear controlled system of differential equations will hit the target set over a finite time interval, despite the uncertainties (noise). Some geometric, pointwise convex constraints on uncertainties are imposed. In the case of a two-dimensional state space a method is proposed for constructing a solvability set without the calculation of the convex hulls of the functions necessary to construct a support function of the geometric difference of the sets. A Hamilton–Jacobi–Bellman type equation is obtained, which is satisfied by the distance function to the solvability set.
- 15 November 2024
- Published by The Russian Academy of Sciences in Дифференциальные уравнения
- Vol. 60 (11) , 1484-1498
ON THE PROPERTIES OF THE SOLVABILITY SET FOR A LINEAR SYSTEM WITH UNCERTAINTY
The work is devoted to the problem of verifying that the state of a linear controlled system of differential equations will hit the target set over a finite time interval, despite the uncertainties (noise). Some geometric, pointwise convex constraints on uncertainties are imposed. In the case of a two-dimensional state space a method is proposed for constructing a solvability set without the calculation of the convex hulls of the functions necessary to construct a support function of the geometric difference of the sets. A Hamilton–Jacobi–Bellman type equation is obtained, which is satisfied by the distance function to the solvability set.
- 1 November 2024
- Published by Pleiades Publishing Ltd in Differential Equations
- Vol. 60 (11) , 1557-1571
On the Properties of the Solvability Set for a Linear System with Uncertainty
The work is devoted to the problem of verifying the fact that the state of a linear controlled system of differential equations hits the target set over a finite time interval despite the uncertainty (noise). Some geometric, pointwise convex constraints on uncertainties are imposed. In the case of a two-dimensional state space a method is proposed for constructing the solvability set without the calculation of the convex hulls of the functions necessary to construct a support function of the geometric difference of the sets. A Hamilton–Jacobi–Bellman type equation is obtained that is satisfied by the distance function to the solvability set.
- 1 November 2024
- Published by Pleiades Publishing Ltd in Differential Equations
- Vol. 60 (11) , 1557-1571
On the Properties of the Solvability Set for a Linear System with Uncertainty
The work is devoted to the problem of verifying the fact that the state of a linear controlled system of differential equations hits the target set over a finite time interval despite the uncertainty (noise). Some geometric, pointwise convex constraints on uncertainties are imposed. In the case of a two-dimensional state space a method is proposed for constructing the solvability set without the calculation of the convex hulls of the functions necessary to construct a support function of the geometric difference of the sets. A Hamilton–Jacobi–Bellman type equation is obtained that is satisfied by the distance function to the solvability set.
- 1 January 2020
- Published by Springer Nature
Dynamic Programming for Impulse Feedback and Fast Controls
- 1 January 2020
- Published by Springer Nature
Dynamic Programming for Impulse Feedback and Fast Controls
- 20 May 2016
- Published by Springer Nature
- p. 525-537
Attenuation of Uncertain Disturbances Through Fast Control Inputs
- 20 May 2016
- Published by Springer Nature
- p. 525-537
Attenuation of Uncertain Disturbances Through Fast Control Inputs
- 1 January 2016
- Published by Springer Nature
- p. 318-332
Techniques for Solving Large-Scale Graph Problems on Heterogeneous Platforms
- 1 January 2016
- Published by Springer Nature
- p. 318-332
Techniques for Solving Large-Scale Graph Problems on Heterogeneous Platforms
- 1 November 2014
- Published by Pleiades Publishing Ltd in Doklady Mathematics
- Vol. 90 (3) , 795-799
Properties of value functions in impulse control problems
- 1 November 2014
- Published by Pleiades Publishing Ltd in Doklady Mathematics
- Vol. 90 (3) , 795-799
Properties of value functions in impulse control problems
- 1 January 2014
- Published by Elsevier in IFAC Proceedings Volumes
- Vol. 47 (3) , 1655-1660
The Specifics of Closed-Loop Impulse Control
- 1 January 2014
- Published by Elsevier in IFAC Proceedings Volumes
- Vol. 47 (3) , 1655-1660
The Specifics of Closed-Loop Impulse Control
- 1 May 2013
- Published by Pleiades Publishing Ltd in Journal of Computer and Systems Sciences International
- Vol. 52 (3) , 365-376
Numerical algorithm for solving the problem of synthesis of impulse controls under uncertainty
Feedback control problem for a linear system under an unknown but bounded disturbance is considered. A numerical algorithm for the synthesis of controls in the problem of impulse control based on the...
- 1 May 2013
- Published by Pleiades Publishing Ltd in Journal of Computer and Systems Sciences International
- Vol. 52 (3) , 365-376
Numerical algorithm for solving the problem of synthesis of impulse controls under uncertainty
Feedback control problem for a linear system under an unknown but bounded disturbance is considered. A numerical algorithm for the synthesis of controls in the problem of impulse control based on the...
- 1 January 2013
- Published by Elsevier in IFAC Proceedings Volumes
- Vol. 46 (23) , 235-240
Nonlinear Feedback Types in Impulse and Fast Control
- 1 January 2013
- Published by Elsevier in IFAC Proceedings Volumes
- Vol. 46 (23) , 235-240
Nonlinear Feedback Types in Impulse and Fast Control