Papers for

systems engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Context operations improve systems design modelling with large language models

Context operations to architecture modelling output from large language models and evaluation criteria for their use in systems engineering design

Abstract: The development of generative artificial intelligence resources enables opportunities of speeding up systems and engineering design work. This contribution introduces a framework of formal operations for assembling context in LLM-based engineering design. This framework involves the assembly of modular context units, including policy prompts, reference units with persistence, and user questions with prompt vectoring. This approach enables the systematic structuring of interactions with generative models. A formal method for evaluating modelling-as-code LLM outputs is also presented, which enables the evaluation of compliance to intent from LLM answers and thereby asses the support from LLMs for systems architecture modelling.

Wed 9 SeptArtificial IntelligenceSoftware Engineering
The gist
Designing complex systems is often slow and complicated. This paper offers a way to structure how large language models (LLMs) are used in engineering design by organizing different types of information like policies and previous references alongside user questions. The authors also propose a method to check if the model’s outputs really match what the designers want. This helps engineers trust and make better use of AI tools when planning system architectures.
Open → 2609.10132v1

Abstract framework organizes analysis of changing time data

Time-Varying Data as Sheaves: an Invitation to Narratives

Abstract: Modern science and engineering increasingly rely on time-varying data, yet the mathematical tools used to model temporal phenomena are often developed within separate disciplines, obscuring common principles and limiting the transfer of ideas across fields. This chapter presents the theory of narratives, an abstract framework for time-varying objects of any mathematical kind that supports both theoretical investigations and applications. To illustrate this perspective, the chapter develops three vignettes, each illustrating a different research direction. The first addresses a general concern: What information loss can occur when switching between different representations of temporal data? The second concerns structural and algorithmic approaches: How can we systematically decompose time-varying data into simple pieces and obtain invariants describing its structural complexity? The third is an application to control theory: How can we model multi-agent systems with switching communication topologies? More important than any individual vignette, the central message of this invitation is that a suitable abstract perspective can organize and guide research across remarkably diverse mathematical and scientific domains.

Tue 8 SeptArtificial IntelligenceMultiagent Systems
The gist
Handling data that changes over time is tricky because different fields use different math tools, making it hard to share ideas. The authors introduce an abstract idea called narratives that can describe any kind of data as it changes over time. They show examples about how changing data can lose information, how to break down complicated time data into simple parts, and how to model systems where groups of agents communicate differently over time. Their main point is that this new way of thinking can help connect different scientific areas that study time-varying data.
Open → 2609.09056v1