Visualizations play a crucial part in effective communication of concepts and information. Recent advances in reasoning and retrieval augmented generation have enabled Large Language Models (LLMs) to perform deep research and generate comprehensive reports. Despite its progress, existing deep research frameworks primarily focus on generating text-only content, leaving the automated generation of interleaved texts and visualizations underexplored. This novel task poses key challenges in designing informative visualizations and effectively integrating them with text reports. To address these challenges, we propose Formal Description of Visualization (FDV), a structured textual representation of charts that enables LLMs to learn from and generate diverse, high-quality visualizations. Building on this representation, we introduce Multimodal DeepResearcher, an agentic framework that decomposes the task into four stages: (1) researching, (2) exemplar report textualization, (3) planning and (4) multimodal report generation. For the evaluation of the generated reports, we develop MultimodalReportBench which contains 100 diverse topics as inputs, and a set of dedicated metrics for report and chart evaluation. Extensive experiments across models and evaluation methods demonstrate the effectiveness of Multimodal DeepResearcher. Notably, utilizing the same Claude 3.7 Sonnet model, Multimodal DeepResearcher achieves an 82% overall win rate over the baseline method.

Yinghao Tang, Xueding Liu, Boyuan Zhang, Tingfeng Lan, Yupeng Xie, Jiale Lao, Yiyao Wang, Haoxuan Li, Tingting Gao, Bo Pan, Luoxuan Weng, Xiuqi Huang, Minfeng Zhu, Yingchaojie Feng, Yuyu Luo, Wei Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Recent advances in large language models (LLMs) have shown great potential in automating the process of visualization authoring through simple natural language utterances. However, instructing LLMs using natural language is limited in precision and expressiveness for conveying visualization intent, leading to misinterpretation and time-consuming iterations. To address these limitations, we conduct an empirical study to understand how LLMs interpret ambiguous or incomplete text prompts in the context of visualization authoring, and the conditions making LLMs misinterpret user intent. Informed by the findings, we introduce visual prompts as a complementary input modality to text prompts, which help clarify user intent and improve LLMs' interpretation abilities. To explore the potential of multimodal prompting in visualization authoring, we design VisPilot, which enables users to easily create visualizations using multimodal prompts, including text, sketches, and direct manipulations on existing visualizations. We evaluate VisPilot through a controlled user study and an expert evaluation. The results suggest that multimodal prompts facilitate users in communicating spatial constraints, local references, and design preferences while maintaining comparable task efficiency to text-only prompting. We further discuss when text, visual, and hybrid prompts are beneficial for visualization authoring, and summarize design implications for future human-AI authoring systems.

Business intelligence (BI) transforms large volumes of data within modern organizations into actionable insights for informed decision-making. Recently, large language model (LLM)-based agents have streamlined the BI workflow by automatically performing task planning, reasoning, and actions in executable environments based on natural language (NL) queries. However, existing approaches primarily focus on individual BI tasks such as NL2SQL and NL2VIS. The fragmentation of tasks across different data roles and tools lead to inefficiencies and potential errors due to the iterative and collaborative nature of BI. In this paper, we introduce DataLab, a unified BI platform that integrates a one-stop LLM-based agent framework with an augmented computational notebook interface. DataLab supports various BI tasks for different data roles in data preparation, analysis, and visualization by seamlessly combining LLM assistance with user customization within a single environment. To achieve this unification, we design a domain knowledge incorporation module tailored for enterprise-specific BI tasks, an inter-agent communication mechanism to facilitate information sharing across the BI workflow, and a cell-based context management strategy to enhance context utilization efficiency in BI notebooks. Extensive experiments demonstrate that DataLab achieves state-of-the-art performance on various BI tasks across popular research benchmarks. Moreover, DataLab maintains high effectiveness and efficiency on real-world datasets from Tencent, achieving up to a 58.58% increase in accuracy and a 61.65 % reduction in token cost on enterprise-specific BI tasks.

The rapid development of large language models (LLMs), such as ChatGPT, has revolutionized the efficiency of creating programming tutorials. LLMs can be instructed with text prompts to generate comprehensive text descriptions for code snippets provided by users. However, the lack of transparency in the end-to-end generation process has hindered the understanding of model behavior and limited user control over the generated results. To tackle this challenge, we introduce a novel approach that breaks down the programming tutorial creation task into actionable steps. By employing the tree-of-thought method, LLMs engage in an exploratory process to generate diverse and faithful programming tutorials. We then present SPROUT, an authoring tool equipped with a series of interactive visualizations that empower users to have greater control and understanding of the programming tutorial creation process. A formal user study demonstrated the effectiveness of SPROUT, showing that our tool assists users to actively participate in the programming tutorial creation process, leading to more reliable and customizable results. By providing users with greater control and understanding, SPROUT enhances the user experience and improves the overall quality of programming tutorial.

The proliferation of large language models (LLMs) has revolutionized the capabilities of natural language interfaces (NLIs) for data analysis. LLMs can perform multi-step and complex reasoning to generate data insights based on users' analytic intents. However, these insights often entangle with an abundance of contexts in analytic conversations such as code, visualizations, and natural language explanations. This hinders efficient recording, organization, and navigation of insights within the current chat-based LLM interfaces. In this paper, we first conduct a formative study with eight data analysts to understand their general workflow and pain points of insight management during LLM-powered data analysis. Accordingly, we introduce InsightLens, an interactive system to overcome such challenges. Built upon an LLM-agent-based framework that automates insight recording and organization along with the analysis process, InsightLens visualizes the complex conversational contexts from multiple aspects to facilitate insight navigation. A user study with twelve data analysts demonstrates the effectiveness of InsightLens, showing that it significantly reduces users' manual and cognitive effort without disrupting their conversational data analysis workflow, leading to a more efficient analysis experience.

Authoring graph visualization requires advanced programming skills, expert domain knowledge, and significant workload. Existing authoring tools either support limited templates of graph visualization, or suffer from a high learning cost. We analyze the design requirements on a tool for graph visualizations, and contribute Nuwa, a user-friendly declarative authoring tool for the interactive specification of graph visualizations in terms of data, entity, change, and encoding. Our implementation empowers users to conveniently create, compare, and modulate comprehensive graph visualizations with a wide range of styles. We showcase various examples to verify the expressiveness of Nuwa. Via an expert interview and the analysis on cognitive dimensions we evaluate the usability of Nuwa.

Data imputation is an essential pre-processing task for data governance, aimed at filling in incomplete data. However, conventional data imputation methods can only partly alleviate data incompleteness using isolated tabular data, and they fail to achieve the best balance between accuracy and efficiency. In this paper, we present a novel visual analysis approach for data imputation. We develop a multi-party tabular data association strategy that uses intelligent algorithms to identify similar columns and establish column correlations across multiple tables. Then, we perform the initial imputation of incomplete data using correlated data entries from other tables. Additionally, we develop a visual analysis system to refine data imputation candidates. Our interactive system combines the multi-party data imputation approach with expert knowledge, allowing for a better understanding of the relational structure of the data. This significantly enhances the accuracy and efficiency of data imputation, thereby enhancing the quality of data governance and the intrinsic value of data assets. Experimental validation and user surveys demonstrate that this method supports users in verifying and judging the associated columns and similar rows using their domain knowledge.

Diagnosing the cluster-based performance of large-scale deep neural network (DNN) models during training is essential for improving training efficiency and reducing resource consumption. However, it remains challenging due to the incomprehensibility of the parallelization strategy and the sheer volume of complex data generated in the training processes. Prior works visually analyze performance profiles and timeline traces to identify anomalies from the perspective of individual devices in the cluster, which is not amenable for studying the root cause of anomalies. In this article, we present a visual analytics approach that empowers analysts to visually explore the parallel training process of a DNN model and interactively diagnose the root cause of a performance issue. A set of design requirements is gathered through discussions with domain experts. We propose an enhanced execution flow of model operators for illustrating parallelization strategies within the computational graph layout. We design and implement an enhanced Marey's graph representation, which introduces the concept of time-span and a banded visual metaphor to convey training dynamics and help experts identify inefficient training processes. We also propose a visual aggregation technique to improve visualization efficiency. We evaluate our approach using case studies, a user study and expert interviews on two large-scale models run in a cluster, namely, the PanGu- α 13B model (40 layers), and the Resnet model (50 layers).

Multiple-view (MV) representations enabling multi-perspective exploration of large and complex data are often employed on 2D displays. The technique also shows great potential in addressing complex analytic tasks in immersive visualization. However, although useful, the design space of MV representations in immersive visualization lacks in deep exploration. In this paper, we propose a new perspective to this line of research, by examining the effects of view layout for MV representations on situated analytics. Specifically, we disentangle situated analytics in perspectives of situatedness regarding spatial relationship between visual representations and physical referents, and analytics regarding cross-view data analysis including filtering, refocusing, and connecting tasks. Through an in-depth analysis of existing layout paradigms, we summarize design trade-offs for achieving high situatedness and effective analytics simultaneously. We then distill a list of design requirements for a desired layout that balances situatedness and analytics, and develop a prototype system with an automatic layout adaptation method to fulfill the requirements. The method mainly includes a cylindrical paradigm for egocentric reference frame, and a force-directed method for proper view-view, view-user, and view-referent proximities and high view visibility. We conducted a formal user study that compares layouts by our method with linked and embedded layouts. Quantitative results show that participants finished filtering- and connecting-centered tasks significantly faster with our layouts, and user feedback confirms high usability of the prototype system.