Get the latest tech news

Towards a science of scaling agent systems: When and why agent systems work


January 28, 2026 Yubin Kim, Research Intern, and Xin Liu, Senior Research Scientist, Google Research Through a controlled evaluation of 180 agent configurations, we derive the first quantitative scaling principles for AI agent systems, revealing that multi-agent coordination dramatically improves performance on parallelizable tasks but degrades it on sequential ones; we also introduce a predictive model that identifies the optimal architecture for 87% of unseen tasks. AI agents — systems capable of reasoning, planning, and acting — are becoming a common paradigm for real-world AI applications.

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of science

science

Photo of agent systems

agent systems

Photo of agent systems work

agent systems work

Related news:

News photo

Exactitude in Science – Borges (1946) [pdf]

News photo

Sandia boffins let three AI agents loose in the lab. Science, not chaos, ensued

News photo

The Science of Fermentation [audio]