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

TL;DR

Glia is an AI system that uses large language models in a multi-agent framework to autonomously design and optimize computer systems, achieving human-level performance and generating interpretable solutions.

Contribution

Introducing Glia, a human-inspired AI architecture employing reasoning and experimentation agents to autonomously create interpretable system designs using LLMs.

Findings

Glia produces request routing, scheduling, and auto-scaling algorithms at human-expert levels.

It generates novel insights into workload behavior.

It significantly reduces design time compared to traditional methods.

Abstract

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.