Assistants, Not Architects: The Role of LLMs in Networked Systems Design

2026-04-28

AI Summary

This work addresses the limitations of large language models (LLMs) in modern network system architecture design, where they often fail due to overlooked constraints and erroneous assumptions. To overcome these issues, the authors propose Kepler, a framework that formulates architecture design as an interpretable constrained optimization problem. Kepler encodes critical properties of systems, hardware, and workloads at an abstract level through expert-driven, structured specifications and leverages SMT solvers for rigorous reasoning. By circumventing the unreliable generative process of LLMs, Kepler efficiently synthesizes feasible architectures that balance multiple objectives, uncovers cross-layer interactions missed by LLMs, and provides traceable, explainable design decisions.

Abstract

Designing the architecture of modern networked systems requires navigating a large, combinatorial space of hardware, systems, and configuration choices with complex cross-layer interactions. Architects must balance competing objectives such as performance, cost, and deployability while satisfying compatibility and resource constraints, often relying on scattered rules-of-thumb drawn from benchmarks, papers, documentation, and expert experience. This raises a natural question: can large language models (LLMs) reliably perform this kind of architectural reasoning? We find that they cannot. While LLMs produce plausible configurations, they frequently miss critical constraints, encode incorrect assumptions, and exhibit ``stickiness'' to familiar patterns. A natural workaround--iterative validation via simulation or experimentation--is often prohibitively expensive at scale and, in many cases, infeasible, particularly when comparing hardware-dependent alternatives. Motivated by this gap, we present Kepler, a lightweight reasoning framework for architecture design that combines structured, expert-driven specifications with SMT-based optimization. Kepler encodes architecturally significant properties--requirements, incompatibilities, and qualitative trade-offs--about systems, hardware, and workloads as constraints, and synthesizes feasible designs that optimize user-defined objectives. It operates at an abstract level, capturing ``rules-of-thumb'' rather than detailed system behavior, enabling tractable reasoning while preserving key interactions, and provides explanations for its decisions. Through experiments and case studies, we show that Kepler uncovers interactions missed by LLMs and supports systematic, explainable design exploration.

Problem

• networked systems design
• architectural reasoning
• large language models
• constraint satisfaction
• design space exploration

Innovation

• SMT-based optimization
• structured specifications
• architectural reasoning
• explainable design
• constraint synthesis