Author name: S. Aaron McClendon, Jorge Gallego-Feliciano, Stavros Zervoudakis, Antonios Saravanos

arXiv:2604.11465v2 Announce Type: replace
Abstract: Large language model (LLM) agents show promise on realistic tool-use tasks, but deploying capable agents on modest hardware remains challenging. We study whether inference-time scaffolding alone, wit…

arXiv:2604.11465v1 Announce Type: new
Abstract: Large language model (LLM) agents show promise on realistic tool-use tasks, but deploying capable agents on modest hardware remains challenging. We study whether inference-time scaffolding alone, without…