---
title: "Study: AI agent 'skills' help via structure, not knowledge, and don't scale well"
url: https://www.parallelquant.com/posts/study-ai-agent-skills-help-via-structure-not-knowledge-and-don-t-scale-w-37cf92
source_name: "The Decoder"
source_url: https://the-decoder.com/study-explains-why-ai-agents-benefit-from-skills-and-when-they-fail/
published: 2026-08-22T12:15:10.000Z
topics: ["research", "llms"]
publisher: "Parallel Quant"
---

# Study: AI agent 'skills' help via structure, not knowledge, and don't scale well

*2026-08-22 · Source: [The Decoder](https://the-decoder.com/study-explains-why-ai-agents-benefit-from-skills-and-when-they-fail/)*

Researchers from Princeton and UC San Diego found that giving AI agents packaged "skills" improves performance mainly by providing structured workflows, not by adding new knowledge. As a skill library grows larger, agents increasingly struggle to find and select the right skill for a given task.

**Why it matters:** This complicates the fast-growing "agent skills" ecosystem by locating the real bottleneck in retrieval and selection rather than skill content itself, meaning bigger skill libraries can hurt as much as help. It reinforces a theme surfacing elsewhere this week: agent harness and workflow design increasingly matter more than raw model capability.

**Topics:** research, llms

---
Read the original: https://the-decoder.com/study-explains-why-ai-agents-benefit-from-skills-and-when-they-fail/
Canonical: https://www.parallelquant.com/posts/study-ai-agent-skills-help-via-structure-not-knowledge-and-don-t-scale-w-37cf92
Published by Parallel Quant — https://www.parallelquant.com