Vadim Potemkin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Vadim Potemkin has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Ilia Revin
ITMO University, St. Petersburg, Russian Federation
2 shared publications - Nikolay O. Nikitin
ITMO University
2 shared publications - Alexander V. Boukhanovsky
ITMO University
1 shared publication - Andrey V. Savchenko
Sber AI Lab, Moscow, Russian Federation, HSE University, Moscow, Russian Federation, and ITMO University, Saint Petersburg, Russian Federation
1 shared publication - Anna Kalyuzhnaya
ITMO University, St. Petersburg, Russian Federation
1 shared publication - Danil Fedorov
ITMO University, St. Petersburg, Russian Federation
1 shared publication
Latest Publications
- Open Access
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1344-1352
Evolving Multi-Agent Systems with Large Language Models: Surrogate Fitness Limitations and Empirical Insights
We investigate the use of large language models (LLMs) as evolutionary operators for optimizing the architecture of multi-agent systems (MAS) - a representative instance of LLM-driven optimization over attributed-graph artifacts that arise in generative design. Given a task description, an initial MAS configuration is generated and then refined on a per-task basis through two optimization strategies: (1) a population-based evolutionary approach where LLMs serve as mutation, crossover, and selection operators, with an LLM-as-a-Judge ensemble providing the surrogate fitness signal; and (2) a simpler iterative regeneration scheme that uses textual feedback from LLM judges to guide single-solution improvement without maintaining a population. We evaluate both approaches on the GAIA benchmark. Our experiments reveal a critical sensitivity to the judge model's quality: a capable judge (Claude 4 Sonnet) yields +14.3 and +6.67 percentage-point accuracy improvements for evolutionary and iterative approaches, respectively, whereas a weaker judge (Gemini-2.5-Flash) provides no benefit or even degrades performance below the unoptimized baseline. Both approaches incur substantial computational costs, raising questions about practical cost-effectiveness. These results highlight fundamental challenges of surrogate fitness functions in LLM-driven evolutionary optimization and offer practical insights for applying evolutionary methods to MAS architecture design.
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1344-1352
Open AccessEvolving Multi-Agent Systems with Large Language Models: Surrogate Fitness Limitations and Empirical Insights
We investigate the use of large language models (LLMs) as evolutionary operators for optimizing the architecture of multi-agent systems (MAS) - a representative instance of LLM-driven optimization over attributed-graph artifacts that arise in generative design. Given a task description, an initial MAS configuration is generated and then refined on a per-task basis through two optimization strategies: (1) a population-based evolutionary approach where LLMs serve as mutation, crossover, and selection operators, with an LLM-as-a-Judge ensemble providing the surrogate fitness signal; and (2) a simpler iterative regeneration scheme that uses textual feedback from LLM judges to guide single-solution improvement without maintaining a population. We evaluate both approaches on the GAIA benchmark. Our experiments reveal a critical sensitivity to the judge model's quality: a capable judge (Claude 4 Sonnet) yields +14.3 and +6.67 percentage-point accuracy improvements for evolutionary and iterative approaches, respectively, whereas a weaker judge (Gemini-2.5-Flash) provides no benefit or even degrades performance below the unoptimized baseline. Both approaches incur substantial computational costs, raising questions about practical cost-effectiveness. These results highlight fundamental challenges of surrogate fitness functions in LLM-driven evolutionary optimization and offer practical insights for applying evolutionary methods to MAS architecture design.
- 6 July 2025
- Published by Springer Nature
- p. 241-248
Rockburst Forecasting Using Composite Modelling for Seismic Sensors Data
- 6 July 2025
- Published by Springer Nature
- p. 241-248
Rockburst Forecasting Using Composite Modelling for Seismic Sensors Data
- Open Access
- 1 January 2022
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Journal of Applied Engineering Science
- Vol. 20 (2) , 624
10.5937/jaes0-31764 = Retraction: Development of method to assess separation process taking into account rheological properties of mineral slurry
This article has been retracted at the request of the Editor-in-Chief, in line with journal Publication Ethics based on guidelines and standards developed by the Committee on Publication Ethics (COPE). This article has been retracted at the request of the authors, because they determined mistakes in conducted research which demand additional check and clarification. Therefore, the results and conclusions could be incorrect. Both authors, Vadim Potemkin and Tatiana Aleksandrova, agree to this retraction. The Authors and Editors would like to apologize to readers for not uncovering these issues during the editorial process.
- 1 January 2022
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Journal of Applied Engineering Science
- Vol. 20 (2) , 624
Open Access10.5937/jaes0-31764 = Retraction: Development of method to assess separation process taking into account rheological properties of mineral slurry
This article has been retracted at the request of the Editor-in-Chief, in line with journal Publication Ethics based on guidelines and standards developed by the Committee on Publication Ethics (COPE). This article has been retracted at the request of the authors, because they determined mistakes in conducted research which demand additional check and clarification. Therefore, the results and conclusions could be incorrect. Both authors, Vadim Potemkin and Tatiana Aleksandrova, agree to this retraction. The Authors and Editors would like to apologize to readers for not uncovering these issues during the editorial process.
- Open Access
- 17 December 2021
- Published by Saint-Petersburg Mining University in Journal of Mining Institute
- Vol. 252, 908-916
Development of a methodology to assess the hydrocyclone process with account of the rheological properties of the mineral slurry
DOI: 10.31897/PMI.2021.6.12 The paper studies the possibility of assessing the separation of mineral raw materials, taking into account the rheology of the mineral slurry. The ores of the Mayskoye deposit were chosen as the object of the study, characterized by a thin impregnation of the valuable component – gold in the host minerals, which determines the use of fine...
- 17 December 2021
- Published by Saint-Petersburg Mining University in Journal of Mining Institute
- Vol. 252, 908-916
Open AccessDevelopment of a methodology to assess the hydrocyclone process with account of the rheological properties of the mineral slurry
DOI: 10.31897/PMI.2021.6.12 The paper studies the possibility of assessing the separation of mineral raw materials, taking into account the rheology of the mineral slurry. The ores of the Mayskoye deposit were chosen as the object of the study, characterized by a thin impregnation of the valuable component – gold in the host minerals, which determines the use of fine...