eess.SY · 2026-08-12 · No. 82
Systems and Control, 2026-08-12.
1 new papers in eess.SY. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
1 entries-
01
Optimal Stopping of Self-Refining Foundation Models
Kim Hammar, Tansu Alpcan, Emil C. Lupu
eess.SY · cs.AI
Foundation models can improve their outputs through a self-refinement process driven by external feedback. In this process, the model is embedded in an iterative loop where it generates outputs, receives feedback from verifiers, and refines its responses through in-context learning. Following a novel approach, we formalize this process as an optimal stopping problem where the number of refinement iterations is decided based on expected...
This edition is part of The Daily Abstract — eess.SY archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.