Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks — Paper

Abstract

How can language model agents effectively leverage libraries of reusable knowledge to solve long-horizon tasks? Recent work has increasingly focused on agent skills: reusable capabilities represented as skill packages, i.e., multi-file bundles containing instructions, scripts, and other resources that help agents perform specific tasks. Agent skills are typically executed by loading their skill instructions into an agent's context and relying on the agent to follow them. As task horizons grow, however, this approach becomes increasingly brittle, because reasoning quality degrades as more information accumulates in the context window. We investigate an alternative approach in which skill packages are instead invoked as subagents. Rather than loading skill instructions into the main context, subagent execution spawns fresh context windows dedicated to solving individual subtasks. We show that subagent execution outperforms agent-skill execution when skill packages expose clear input-output contracts and their instructions encode the procedural knowledge needed to fulfill those contracts. The tradeoff is additional communication overhead, as extra tokens are required to coordinate between the main agent and its subagents. Our results show that the benefit of reusable knowledge depends not only on its content, but also on how it is organized and invoked.

Authors 5

Wasu Top Piriyakulkij, Rachel Lawrence, Alicia Curth, Sushrut Karmalkar, Niranjani Prasad

Specification

Official page: arxiv.org/abs/2609.09233
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Arxiv announce type: new
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
arXiv id: 2609.09233
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Categories: cs.AI, cs.CL, cs.LG
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
PDF: arxiv.org/pdf/2609.09233
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Primary category: cs.AI
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Published: 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

7 h ago

Conflicts

None

No models linked to this paper yet.

Authors: Wasu Top Piriyakulkij, Rachel Lawrence, Alicia Curth

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Authors

1 claims · 1 propertiesShow all properties

Authorsauthors1

Claim history for Authors
Value	Valid from → to	Status	Source	Confidence	Extractor
Wasu Top Piriyakulkij, Rachel Lawrence, Alicia Curth, Sushrut Karmalkar, Niranjani Prasad	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
New paperPaperSubagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks
New paper: Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks
arxiv
rss.arxiv.org

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.AI	feed	T1· Official	5 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.