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

arXiv: https://arxiv.org/abs/2604.25506 · HTML: https://mlsanity.com/paper/2604.25506/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 61 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Builds on (most cited first, 11 of 11)

- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.06941/) (2025)
- [Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming](https://mlsanity.com/paper/2410.12112/) (2024)
- [Glia: A Human-Inspired AI for Automated Systems Design and Optimization](https://mlsanity.com/paper/2510.27176/) (2025)
- [Homa: A Receiver-Driven Low-Latency Transport Protocol Using Network Priorities (Complete Version)](https://mlsanity.com/paper/1803.09615/) (2018)
- [Expanding across time to deliver bandwidth efficiency and low latency](https://mlsanity.com/paper/1903.12307/) (2019)
- [AI-Driven Research for Databases](https://mlsanity.com/paper/2604.06566/) (2026)
- [Merlin: A Language for Provisioning Network Resources](https://mlsanity.com/paper/1407.1199/) (2014)
- [Verifying Reachability in Networks with Mutable Datapaths](https://mlsanity.com/paper/1607.00991/) (2016)
- [An Open-Source Benchmark Suite for Cloud and IoT Microservices](https://mlsanity.com/paper/1905.11055/) (2019)
- [Plankton: Scalable network configuration verification through model checking](https://mlsanity.com/paper/1911.02128/) (2019)

## Abstract (arXiv)

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.