Glia: A Human-Inspired AI for Automated Systems Design and Optimization
This addresses the challenge of automating complex systems design for AI/ML infrastructure, though it builds incrementally on existing LLM and multi-agent approaches.
The paper tackles the problem of automated design of computer systems by introducing Glia, an AI architecture that uses large language models in a multi-agent workflow to generate interpretable designs for distributed GPU clusters. The result is new algorithms for request routing, scheduling, and auto-scaling that perform at human-expert levels in significantly less time.
Can an 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 process. 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 by combining reasoning LLMs with structured experimentation, an AI can produce creative and understandable designs for complex systems problems.