Glia: A Human-Inspired AI for Automated Systems Design and Optimization

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hamadanian, Pouya, Karimi, Pantea, Nasr-Esfahany, Arash, Noorbakhsh, Kimia, Chandler, Joseph, ParandehGheibi, Ali, Alizadeh, Mohammad, Balakrishnan, Hari
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912999746306048
author Hamadanian, Pouya
Karimi, Pantea
Nasr-Esfahany, Arash
Noorbakhsh, Kimia
Chandler, Joseph
ParandehGheibi, Ali
Alizadeh, Mohammad
Balakrishnan, Hari
author_facet Hamadanian, Pouya
Karimi, Pantea
Nasr-Esfahany, Arash
Noorbakhsh, Kimia
Chandler, Joseph
ParandehGheibi, Ali
Alizadeh, Mohammad
Balakrishnan, Hari
contents Can AI autonomously design mechanisms for computer systems on par with the creativity and reasoning of human experts? We present Glia, an AI architecture for networked systems design that uses large language models (LLMs) in a human-inspired multi-agent workflow. Each agent specializes in reasoning, experimentation, and analysis, collaborating through an evaluation framework that grounds abstract reasoning in empirical feedback. Unlike prior ML-for-systems methods that optimize black-box policies, Glia generates interpretable designs and exposes its reasoning. When applied to a distributed GPU cluster for LLM inference, it produces new algorithms for request routing, scheduling, and auto-scaling that perform at human-expert levels in significantly less time, while yielding novel insights into workload behavior. Our results suggest that combining reasoning LLMs with structured experimentation, an AI can produce creative and understandable designs for complex systems problems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_27176
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Glia: A Human-Inspired AI for Automated Systems Design and Optimization
Hamadanian, Pouya
Karimi, Pantea
Nasr-Esfahany, Arash
Noorbakhsh, Kimia
Chandler, Joseph
ParandehGheibi, Ali
Alizadeh, Mohammad
Balakrishnan, Hari
Artificial Intelligence
Computation and Language
Distributed, Parallel, and Cluster Computing
Can AI autonomously design mechanisms for computer systems on par with the creativity and reasoning of human experts? We present Glia, an AI architecture for networked systems design that uses large language models (LLMs) in a human-inspired multi-agent workflow. Each agent specializes in reasoning, experimentation, and analysis, collaborating through an evaluation framework that grounds abstract reasoning in empirical feedback. Unlike prior ML-for-systems methods that optimize black-box policies, Glia generates interpretable designs and exposes its reasoning. When applied to a distributed GPU cluster for LLM inference, it produces new algorithms for request routing, scheduling, and auto-scaling that perform at human-expert levels in significantly less time, while yielding novel insights into workload behavior. Our results suggest that combining reasoning LLMs with structured experimentation, an AI can produce creative and understandable designs for complex systems problems.
title Glia: A Human-Inspired AI for Automated Systems Design and Optimization
topic Artificial Intelligence
Computation and Language
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2510.27176