Large Language Models (LLMs) show great promise as a powerful tool for scientific literature exploration. However, their effectiveness in providing scientifically accurate and comprehensive answers to complex questions within specialized domains remains an active area of research. Using the field of high-temperature cuprates as an exemplar, we evaluate the ability of LLM systems to understand the literature at the level of an expert. We construct an expert-curated database of 1,726 scientific papers that covers the history of the field, and a set of 67 expert-formulated questions that probe deep understanding of the literature. We then evaluate six different LLM-based systems for answering these questions, including both commercially available closed models and a custom retrieval-augmented generation (RAG) system capable of retrieving images alongside text. Experts then evaluate the answers of these systems against a rubric that assesses balanced perspectives, factual comprehensiveness, succinctness, and evidentiary support. Among the six systems two using RAG on curated literature outperformed existing closed models across key metrics, particularly in providing comprehensive and well-supported answers. We discuss promising aspects of LLM performances as well as critical short-comings of all the models. The set of expert-formulated questions and the rubric will be valuable for assessing expert level performance of LLM based reasoning systems.

Spatio-temporal data captures complex dynamics across both space and time, yet traditional visualizations are complex, require domain expertise and often fail to resonate with broader audiences. Here, we propose MapMuse, a storytelling-based framework for interpreting spatio-temporal datasets, transforming them into compelling, narrative-driven experiences. We utilize large language models and employ retrieval augmented generation (RAG) and agent-based techniques to generate comprehensive stories. Drawing on principles common in cinematic storytelling, we emphasize clarity, emotional connection, and audience-centric design. As a case study, we analyze a dataset of taxi trajectories. Two perspectives are presented: a captivating story based on a heat map that visualizes millions of taxi trip endpoints to uncover urban mobility patterns; and a detailed narrative following a single long taxi journey, enriched with city landmarks and temporal shifts. By portraying locations as characters and movement as plot, we argue that data storytelling drives insight, engagement, and action from spatio-temporal information. The case study illustrates how MapMuse can bridge the gap between data complexity and human understanding. The aim of this short paper is to provide a glimpse to the potential of the cinematic storytelling technique as an effective communication tool for spatio-temporal data, as well as to describe open problems and opportunities for future research.

Data visualization is a fundamental tool in genomics research, enabling the exploration, interpretation, and communication of complex genomic features. While machine learning models show promise for transforming data into insightful visualizations, current models lack the training foundation for domain-specific tasks. In an effort to provide a foundational resource for genomics-focused model training, we present a framework for generating a dataset that pairs abstract, low-level questions about genomics data with corresponding visualizations. Building on prior work with statistical plots, our approach adapts to the complexity of genomics data and the specialized representations used to depict them. We further incorporate multiple linked queries and visualizations, along with justifications for design choices, figure captions, and image alt-texts for each item in the dataset. We use genomics data retrieved from three distinct genomics data repositories (4DN, ENCODE, Chromoscope) to produce GQVis: a dataset consisting of 1.14 million single-query data points, 628k query pairs, and 589k query chains. The GQVis dataset and generation code are available at https://huggingface.co/datasets/HIDIVE/GQVis and https://github.com/hms-dbmi/GQVis-Generation.

In this short paper, we present work evaluating an AI agent's understanding of spoken conversations about data visualizations in an online meeting scenario. There is growing interest in the development of AI-assistants that support meetings, such as by providing assistance with tasks or summarizing a discussion. The quality of this support depends on a model that understands the conversational dialogue. To evaluate this understanding, we introduce a dual-axis testing framework for diagnosing the AI agent's comprehension of spoken conversations about data. Using this framework, we designed a series of tests to evaluate understanding of a novel corpus of 72 spoken conversational dialogues about data visualizations. We examine diverse pipelines and model architectures, LLM vs VLM, and diverse input formats for visualizations (the chart image, its underlying source code, or a hybrid of both) to see how this affects model performance on our tests. Using our evaluation methods, we found that text-only input modalities achieved the best performance (96%) in understanding discussions of visualizations in online meetings.

Deep research has revolutionized data analysis, yet data scientists still devote substantial time to manually crafting visualizations, highlighting the need for robust automation from natural language queries. However, current systems struggle with complex datasets containing multiple files and iterative refinement. Existing approaches, including simple single- or multi-agent systems, often oversimplify the task, focusing on initial query parsing while failing to robustly manage data complexity, code errors, or final visualization quality. In this paper, we reframe this challenge as a collaborative multi-agent problem. We introduce CoDA, a multi-agent system that employs specialized LLM agents for metadata analysis, task planning, code generation, and self-reflection. We formalize this pipeline, demonstrating how metadata-focused analysis bypasses token limits and quality-driven refinement ensures robustness. Extensive evaluations show CoDA achieves substantial gains in the overall score, outperforming competitive baselines by up to 41.5%. This work demonstrates that the future of visualization automation lies not in isolated code generation but in integrated, collaborative agentic workflows.

Data visualization is essential for interpreting complex datasets, yet traditional tools often require technical expertise, limiting accessibility. VizGen is an AI-assisted graph generation system that empowers users to create meaningful visualizations using natural language. Leveraging advanced NLP and LLMs like Claude 3.7 Sonnet and Gemini 2.0 Flash, it translates user queries into SQL and recommends suitable graph types. Built on a multi-agent architecture, VizGen handles SQL generation, graph creation, customization, and insight extraction. Beyond visualization, it analyzes data for patterns, anomalies, and correlations, and enhances user understanding by providing explanations enriched with contextual information gathered from the internet. The system supports real-time interaction with SQL databases and allows conversational graph refinement, making data analysis intuitive and accessible.

We present a web-based environment that connects annotation, abstraction, and argumentation during the interpretation of text. As a visual interface for scholarly reading and writing, Textarium combines human analysis with lightweight computational processing to bridge close and distant reading practices. Readers can highlight text, group keywords into concepts, and embed these observations as anchors in essays. The interface renders these interpretive actions as parameterized visualization states. Through a speculative design process of co-creative and iterative prototyping, we developed a reading-writing approach that makes interpretive processes transparent and shareable within digital narratives.

What if the patterns hidden within dialogue reveal more about communication than the words themselves? We introduce Conversational DNA, a novel visual language that treats any dialogue -- whether between humans, between human and AI, or among groups -- as a living system with interpretable structure that can be visualized, compared, and understood. Unlike traditional conversation analysis that reduces rich interaction to statistical summaries, our approach reveals the temporal architecture of dialogue through biological metaphors. Linguistic complexity flows through strand thickness, emotional trajectories cascade through color gradients, conversational relevance forms through connecting elements, and topic coherence maintains structural integrity through helical patterns. Through exploratory analysis of therapeutic conversations and historically significant human-AI dialogues, we demonstrate how this visualization approach reveals interaction patterns that traditional methods miss. Our work contributes a new creative framework for understanding communication that bridges data visualization, human-computer interaction, and the fundamental question of what makes dialogue meaningful in an age where humans increasingly converse with artificial minds.

Making a good graphic that accurately and efficiently conveys the desired message to the audience is both an art and a science, typically not taught in the data science curriculum. Visualisation makeovers are exercises where the community exchange feedback to improve charts and data visualizations. Can multi-modal large language models (LLMs) emulate this task? Given a plot in the form of an image file, or the code used to generate it, an LLM, primed with a list of visualization best practices, is employed to semi-automatically generate constructive criticism to produce a better plot. Our system is centred around prompt engineering of a pre-trained model, relying on a combination of userspecified guidelines and any latent knowledge of data visualization practices that might lie within an LLMs training corpus. Unlike other works, the focus is not on generating valid visualization scripts from raw data or prompts, but on educating the user how to improve their existing data visualizations according to an interpretation of best practices. A quantitative evaluation is performed to measure the sensitivity of the LLM agent to various plotting issues across different chart types. We make the tool available as a simple self-hosted applet with an accessible Web interface.