Related papers: Towards Robust Real-World Spreadsheet Understandin…

Spreadsheets are ubiquitous across the World Wide Web, playing a critical role in enhancing work efficiency across various domains. Large language model (LLM) has been recently attempted for automatic spreadsheet manipulation but has not…

Spreadsheet programming is challenging. Programmers use spreadsheet programming knowledge (e.g., formulas) and problem-solving skills to combine actions into complex tasks. Advancements in large language models have introduced language…

Understanding and reasoning over complex spreadsheets remain fundamental challenges for large language models (LLMs), which often struggle with accurately capturing the complex structure of tables and ensuring reasoning correctness. In this…

Spreadsheet systems (e.g., Microsoft Excel, Google Sheets) play a central role in modern data-centric workflows. As AI agents grow increasingly capable of automating complex tasks, such as controlling computers and generating presentations,…

Spreadsheets are characterized by their extensive two-dimensional grids, flexible layouts, and varied formatting options, which pose significant challenges for large language models (LLMs). In response, we introduce SpreadsheetLLM,…

We present SheetMind, a modular multi-agent framework powered by large language models (LLMs) for spreadsheet automation via natural language instructions. The system comprises three specialized agents: a Manager Agent that decomposes…

There is an overlooked iceberg of problems in end user computing. Spreadsheets are developed by people who are very skilled in their main job function, be it finance, procurement, or production planning, but often have had no formal…

Recent research has explored the use of Large Language Models (LLMs) for tackling complex graph reasoning tasks. However, due to the intricacies of graph structures and the inherent limitations of LLMs in handling long text, current…

We introduce SpreadsheetBench, a challenging spreadsheet manipulation benchmark exclusively derived from real-world scenarios, designed to immerse current large language models (LLMs) in the actual workflow of spreadsheet users. Unlike…

Document Question Answering (DocQA) is a very common task. Existing methods using Large Language Models (LLMs) or Large Vision Language Models (LVLMs) and Retrieval Augmented Generation (RAG) often prioritize information from a single…

Large language models (LLMs) are increasingly tasked with producing and manipulating structured artifacts. We consider the task of end-to-end spreadsheet generation, where language models are prompted to produce spreadsheet artifacts to…

While large language model-based multi-agent systems have shown strong potential for complex reasoning, how to effectively organize multiple agents remains an open question. In this paper, we introduce OrgAgent, a company-style hierarchical…

Recent multimodal LLMs have shown promise in chart-based visual question answering, but their performance declines sharply on unannotated charts-those requiring precise visual interpretation rather than relying on textual shortcuts. To…

Large Language Model (LLM) agents are rapidly improving to handle increasingly complex web-based tasks. Most of these agents rely on general-purpose, proprietary models like GPT-4 and focus on designing better prompts to improve their…

Recent progress in large language models (LLMs) has enabled substantial advances in solving mathematical problems. However, existing benchmarks often fail to reflect the complexity of real-world problems, which demand open-ended,…

Document understanding is a long standing practical task. Vision Language Models (VLMs) have gradually become a primary approach in this domain, demonstrating effective performance on single page tasks. However, their effectiveness…

Real-world design documents (e.g., posters) are inherently multi-layered, combining decoration, text, and images. Editing them from natural-language instructions requires fine-grained, layer-aware reasoning to identify relevant layers and…

Agentic AI has significantly extended the capabilities of large language models (LLMs) by enabling complex reasoning and tool use. However, most existing frameworks are tailored to domains such as mathematics, coding, or web automation, and…

Designing realistic multi-object scenes requires not only generating images, but also planning spatial layouts that respect semantic relations and physical plausibility. On one hand, while recent advances in diffusion models have enabled…

Open data repositories hold potential for evidence-based decision-making, yet are inaccessible to non-experts lacking expertise in dataset discovery, schema mapping, and statistical analysis. Large language models show promise for…