Skip to content

Radar ·

Analyzing the scaling of agent systems

The article presents quantitative principles for modeling how coordination, model capacity, and system and task factors affect agent performance.

Published on December 11, 2025, the article proposes quantitative scaling principles to model how agent-system performance varies with coordination, model capacity, and measurable system and task factors. The evaluation covers 260 configurations, six agent benchmarks, and five architectures.

The work may help engineers analyze these relationships, but the available summary does not detail results by configuration or say which architecture performed best. To consult and verify the findings, read the original article and check its methods, metrics, and results for the 260 configurations, six benchmarks, and five architectures.

Original source: Um modelo preditivo para escalar sistemas de agentes

Curation · AgentLog

Get the essentials

Privacy, AI engineering and security in your inbox.

At most one digest per day, when there is news. Cancel at any time. We use your account's verified email.

Privacy

Looking for something else?DocumentationContact