76‐1: LLM‐based Dynamic Hierarchical RL for Display Manufacturing
SID Symposium Digest of Technical Papers · 2026-06 · 57 (1) · 1043-1046
DOI: 10.1002/sdtp.70001_284 ↗Kurz gefasst
Fachartikel in der Zeitschrift SID Symposium Digest of Technical Papers, online erschienen am 11.09.2026. Verfasst von Youngtaek Seo und 1 weiteren Autor:innen. Die Arbeit nennt 12 Literaturangaben.
Abstract (Originalsprache)
This paper proposes an LLM‐based dynamic HRL framework addressing sparse rewards and stability in applying Deep Reinforcement Learning to display manufacturing. The LLM orchestrates strategic scheduling directions while the HRL agent executes tactical decisions. Validated in a high‐fidelity digital‐twin, this approach reduced urgent‐lot cycle time by 24.05% and variance by 64.92%, demonstrating practical viability for real‐world scheduling applications.
Zitieren
APA
Seo, Y., & Noh, S. D. (2026). 76‐1: LLM‐based Dynamic Hierarchical RL for Display Manufacturing. SID Symposium Digest of Technical Papers, 57(1), 1043-1046. https://doi.org/10.1002/sdtp.70001_284
Vancouver
Seo Y, Noh SD. 76‐1: LLM‐based Dynamic Hierarchical RL for Display Manufacturing. SID Symposium Digest of Technical Papers. 2026;57(1):1043-1046. doi:10.1002/sdtp.70001_284
BibTeX
@article{Seo2026,
author = {Seo, Youngtaek and Noh, Sang Do},
title = {76‐1: LLM‐based Dynamic Hierarchical RL for Display Manufacturing},
journal = {SID Symposium Digest of Technical Papers},
year = {2026},
volume = {57},
number = {1},
pages = {1043--1046},
doi = {10.1002/sdtp.70001_284}
}
EUVIMED