# Researchers Find Agent Skills Work Better as Subagents Than as Context Injections

A Cornell and Microsoft Research paper argues fresh context windows beat loading skill instructions into a growing main context, when skills expose clear input-output contracts.

- Published: 2026-09-11T06:22:22.078Z
- Canonical: https://polylog.news/ai/2026-09-11/researchers-find-agent-skills-work-better-as-subagents-than
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.AI](https://arxiv.org/abs/2609.09233), [arXiv (full text)](https://arxiv.org/html/2609.09233)

A team from Cornell University and Microsoft Research, led by Wasu Top Piriyakulkij, examines a question every agent developer encounters in practice: when an agent has a library of reusable skills, should it read the skill instructions its…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-11/researchers-find-agent-skills-work-better-as-subagents-than (subscription information: https://polylog.news/pricing).