Papers for

software documentation teams

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.

Local large language models generate digital twin reports efficiently

DTScribe: Generating Models for Digital Twin Reporting using Local Large Language Models

Abstract: The development of a digital twin brings together many stakeholders and technical components. We have previously investigated the reporting of the conceptual architecture for these digital twins as an artifact for discussion. However, we find that the activity of modeling the digital twin for visualization and consensus-building can be quite tedious and time-consuming. In this article, we explore the automation of model generation using large language models, targeting the model required for digital twin reporting. Our approach is designed to ingest digital twin documents and output both the conceptual architecture visualization and a reporting page for that digital twin. We first extract from the input the key details aligning with our twenty-one-characteristic Digital Twin Description Framework described in previous work. Then, we generate a description model in the Ontological Modeling Language, representing the digital twin as a constellation of models, data, enablers, and services. We utilize refinement loops with large language models acting as judges and ontological reasoning to increase artifact quality as measured by our metrics. We investigate how architectural and parameter choices affect artifact quality, such as how refinement loops enable local large language models to produce sufficiently high-quality results comparable to larger models. We also detail insights and lessons learned useful for practitioners, such that they can integrate our techniques to accelerate their digital twin reporting or for other model generation tasks. These insights include the use of medium-sized local models (around 20 billion parameters), the avoidance of large language models as judges and clustering for characteristic extraction, and the recommendation of at least two reasoner loops for Ontological Modeling Language refinement.

Tue 13 OctSoftware EngineeringArtificial Intelligence
The gist
Creating digital twins—detailed computer models of real-world objects or systems—requires a lot of manual work to make visual models and reports. The authors found a way to use large language models running locally on computers to automate this process by reading documents and producing detailed models and reports. Their method improves the model quality through repeated checking and reasoning steps, which makes the automated reports almost as good as ones made with bigger, more expensive AI models. They also share practical advice on which models and techniques work best for this task, helping others save time when documenting digital twins.
Open → 2610.18635v1

Flowchart relayout adapts diagrams for any display format

One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipeline

Abstract: Pipeline figures in ML papers must be repurposed across many canvases, including paper columns, 16:9 slides, portrait posters, 1:1 social teasers, 9:16 phone previews. Each format imposes a different aspect ratio on the same computational graph, where any silently broken connection misrepresents the method. We formulate aspect-ratio-adaptive flowchart relayout as a distinct task: given a raster flowchart and a target ratio, produce a structurally faithful, hallucination-free, editable layout. Existing methods fail characteristically: image-to-image models stretch blocks and reject extreme ratios, text-to-image agentic systems hallucinate content, and parse-then-render systems mis-route edges. We propose an agentic pipeline factored into Parse, Style, and Layout stages, each pairing a main agent with a critic that combines deterministic constraint checks with VLM visual feedback so connectivity is explicitly checked and prevented from being silently broken. Outputs are draw.io-editable mxGraph XML. On a curated benchmark of 100 flowcharts at five aspect ratios, evaluated by Gemini 3.1 Pro and validated against human judgments, our method reaches 68.6% Content Fidelity versus 11.2-41.4% for prior work. Project page: https://onefigureeverycanvas.vercel.app/

Mon 5 OctComputer Vision and Pattern RecognitionArtificial Intelligence
The gist
Flowcharts in machine learning papers often need to be shown in many different shapes and screen sizes, like slides, posters, or social media previews. Changing their size can break connections or make parts look stretched, which confuses understanding. The authors created a process that reads the original flowchart image, checks that the connections remain correct, and produces editable diagrams that fit any shape without errors or fake details. Their method scored much higher than previous attempts on keeping the content accurate and easy to edit.
Open → 2610.06852v1

Framework improves scientific method diagrams with reusable skills

SIVIA-RSI: Source-Grounded Adaptation of Diagramming Skills

Abstract: Scientific method diagrams express computations through entities, dependencies, and conditional routes. Although generated figures can be improved through repeated editing, it is less clear whether experience from one paper improves the first figure of another. We present \sys, a framework for source-grounded adaptation of reusable diagramming skills, and study transfer through a complete-candidate evaluation. The framework links critiques to source passages, proposes bounded edits to a persistent skill library, and separates candidate competition from skill acceptance. We evaluate the original skill and four learned candidates on two NLP and language-agent papers, with two fresh generations per condition. The strongest candidate attains 87.50\% required-relation accuracy compared with 83.33\% for the original, while candidate behavior differs across papers. Local improvements on a separate development paper and automatic selector preferences do not establish consistent transfer. Tracing all 22 non-correct relation judgments to their production prompts reveals both incomplete conditional specifications and ambiguities despite explicit instructions. All ten planning diagrams leave an already-terminal selected leaf's route unclear; none of their prompts explicitly binds that route. Our findings show why evaluating reusable diagram skills requires source-grounded relation assessment, complete candidate coverage, and inspection of both prompts and images. We provide all twenty transfer outputs, skill snapshots, assessment records, and executable analyses.

Sun 27 SeptGraphicsMultiagent Systems
The gist
Scientific method diagrams show how ideas or computations flow using entities and connections, but making these diagrams better can be tricky. The authors created a system called SIVIA-RSI that learns from previous diagram improvements to help make better first drafts for new papers. They tested this system on papers about language processing and found the learned skills improved diagram accuracy a bit but did not always work consistently across topics. They also found some challenges arise because instructions and diagrams sometimes leave parts unclear. Their work helps show why checking diagrams closely and connecting them to the original text is important for improving reusable diagram skills.
Open → 2609.33386v1