Vitalii Belov

Vitalii Belov

Auto-generated profile, based on publicly available information

Vitalii Belov

Sber AI, Moscow, Russian Federation and Moscow Institute of Physics and Technology, Dolgoprudny, Russian Federation

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

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

Representative Publications

View All Publications
19 July 2026
Verified
Conference Paper
Open access
VBVitalii Belov
Vitalii Belov
ASArtyom Sosedka
Artyom Sosedka
ASAndrey Sakhovskiy
Andrey Sakhovskiy
EKElizaveta Kovtun
Elizaveta Kovtun
ABArtyom Boyarskikh
Artyom Boyarskikh
Semen BudennyySemen Budennyy
Semen Budennyy
Large language model (LLM) agents improve task performance by decomposing problems into role-specialized behaviors. However, their practical deployment is often limited by the computational cost and instability associated with the on-the-fly agent design for each user request. To address this, we present LLM Agents Factory, a retrieval-based framework that constructs domain-specific and Wikipedia-grounded agents on demand using a base of over 20K predetermined agent profiles. Our framework supports two modes: (1) agent profile retrieval via semantic search and (2) distillation into a compact model fine-tuned for direct agent generation. Experiments on MMLU, BIG-bench, and BIG-bench Hard in a single-agent scenario demonstrate that our retrieval-based agent construction surpasses non-agent baselines in accuracy while matching AutoGen generation quality with a 120B backbone at a substantially lower inference cost. Our work reveals that retrieval from a structured agent repository provides a cost-efficient, accurate, and controllable alternative to dynamic agent generation, responding to the strict demands of industrial applications. We provide the implementation code and the agent base in https://huggingface.co/frontier-ai/llm-agent-factory.