Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks
arXiv 2609.09233v1•573b73210902c9c7ffa9415dcfa421f22f63d855a86b827b1c0766d5dde0a127
Paper metadata
- arXiv ID
- 2609.09233
- Version
- v1
- Category
- cs.AI, cs.CL, cs.LG
- Authors
- Wasu Top Piriyakulkij, Rachel Lawrence, Alicia Curth, Sushrut Karmalkar, Niranjani Prasad
- Publication date
- 2026-09-10T04:00:00Z
- Source identifier
- 2609.09233v1
- Public record ID
- record:sha256:573b73210902c9c7ffa9415dcfa421f22f63d855a86b827b1c0766d5dde0a127
The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.
This is source-provided metadata, not an enriched summary or an impact assessment. Follow the canonical source link for the published material.
Evidence and limitations
- Source ID
- arxiv_research
- Record identifier
- 573b73210902c9c7ffa9415dcfa421f22f63d855a86b827b1c0766d5dde0a127
- Record type
- Source metadata
This record may overlap with other records. Source metadata can be incomplete or change. Validate consequential decisions against the linked source and your own environment.