Record · corpus.blog/posts/01a07d5d-9bfe-73b8-8ed5-779b6d7142a5

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

Google Research · published 28 January 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at research.google Wayback capture

6blogs citing

First cited: 4 Feb 2026
Most recent: 8 Sept 2026
Rank this month: not ranked
Links from this post: 9
Words captured: 981

Cited by

Blog

In the post

Date

Level Up Coding

I Audited 4,523 AI Judgments. Here’s What I’d Check Before Trusting an Agent Team. Read at the source ↗

8 Sept 2026

terratauri.com

Scaling Out Read at the source ↗

1 Sept 2026

marvinzhang.dev

Why AI Agent Teams Can't Escape the Mythical Man-Month Read at the source ↗

13 Jul 2026

designative.info

From Behavior to Judgment: Designing Evaluation for Agentic Systems Read at the source ↗

21 Apr 2026

miadowicz.com

The Age of Amplification: What I See Coming in AI by 2030 (And Why Most People Are Looking at It Wrong) Read at the source ↗

6 Feb 2026

seroter.com

Daily Reading List – February 3, 2026 (#713) Read at the source ↗

4 Feb 2026

Links from this post

Link

Host

https://codeassist.google/

codeassist.google

https://research.google/blog/the-anatomy-of-a-personal-health-agent/

research.google

https://arxiv.org/abs/2402.05120

arxiv.org

https://arxiv.org/abs/2406.07155

arxiv.org

https://arxiv.org/abs/2512.08296

arxiv.org

https://www.vals.ai/benchmarks/finance_agent

vals.ai

https://arxiv.org/pdf/2508.06600

arxiv.org

https://arxiv.org/abs/2412.21033

arxiv.org

https://arxiv.org/abs/2405.00823

arxiv.org