Spreadsheets and End-User Computing

Últimos artículos

• The Last Mile Is the File: OfficeEditBench for Preservation-Aware Office Editing

  Zhiwen Wu, Chengxu Wu · 30 de septiembre de 2026

  A small Office edit creates two obligations: propagate every required update and leave protected state untouched. Updating too little leaves dependencies inconsistent; updating too much changes content the user did not authorize. We introduce OfficeEditBench, a 170-task benchmark for change-scoped m…

• Anatomy of a Spreadsheet Failure, Analysing the EuSpRIG Horror Story Corpus

  Simon Thorne, Angela Collins · 29 de septiembre de 2026

  Spreadsheet disasters have been documented for more than thirty years, but they have not gone away. This paper examines the EuSpRIG horror stories archive as evidence of how ordinary spreadsheets fail and the consequences that follow. After cleaning and deduplication, 121 incidents from 1995 to 2026…

• SheetMind: Actions Set Accuracy, Agents Set the Failure Mode

  Lyuhao Chen, Xi Cheng, Yanming Kang, Ruiyan Zhu, Ke Liu, Rakesh Chowdary Machineni, Yulang Fei, Brian Zhu, Daniel Jin, Binze Cai, Zheng Qi, Neeraj Parihar, Zhoutian Xu, Oliver Gao · 25 de septiembre de 2026

  Spreadsheet agents are converging on elaborate multi-agent designs, yet it is unclear how much of their performance comes from the agents rather than from the action interface they share. We answer this with SheetMind, a Manager-Action-Reflection framework, in a controlled study over all 221 tasks o…

• Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure

  Zofia Smole\'n · 18 de septiembre de 2026

  Semantic cell annotation improves chunking interpretability for spreadsheets in LLM-driven RAG systems, aiding answer generation through enriched context rather than improved retrieval accuracy. We propose a novel framework of splitting any spreadsheet into interpretable chunks using cell role annot…

• Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy

  Saleh Afzoon, Ali Shahsavandi, Phuong Thao Huynh, Melika Zare, Zahra Jahanandish, Amin Beheshti, Usman Naseem · 3 de septiembre de 2026

  AI copilots represent a new generation of AI-powered systems designed to assist users, particularly knowledge workers and developers, in complex, context-rich tasks. As these systems become more embedded in daily workflows, personalization has emerged as a critical factor for improving usability, ef…

• TrustDABench: Benchmarking Reliability and Robustness of LLMs for Structured Data Analysis

  Boshen Shi, Yize Liu, Chen Zhao, Ce Chi, Zhendong Wang, Xing Wang, Junlan Feng · 26 de agosto de 2026

  LLMs are increasingly used to analyze spreadsheets, CSV files, and other structured data, but producing a correct-looking answer is not the same as producing a trustworthy analysis. A trustworthy result should be supported by a valid path from the user question to the relevant data evidence. This re…

• Software Engineering for AI-driven Building Operation

  Philipp Zech, Sascha Hammes, Johannes Weninger, Jürgen Pannosch, Gernot Steidl · 18 de agosto de 2026

  Building operations are energy-inefficient. Artificial Intelligence (AI)-driven control systems promise benefits through optimization and predictive control, but deploying them in real buildings reveals a significant software engineering (SE) challenge. SE for AI practices assume digital environment…

• Walk Before You Run: The Importance of Data Exploration for Data Analysis Agents

  Yike Yuan, Virum Ranka, Tina Lasisi, Lin Ma · 18 de agosto de 2026

  LLM-based data-analysis tools are increasingly used to help users analyze messy spreadsheets and workbooks, from answering questions over uploaded files to generating code, summaries, and visualizations. These systems are often evaluated by the correctness of their final downstream answers. However,…

• SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning

  Panjing He, Mingyue Cheng, Yucong Luo, Li Li, Xiaohan Zhang · 17 de agosto de 2026

  Spreadsheets are widely used to organize, analyze, and manipulate semi-structured data, yet automated spreadsheet reasoning remains challenging for large language models (LLMs). Real-world workbooks often contain implicit cross-table associations, fine-grained column dependencies, and complex spatia…

• Back to the Future: A workbook time machine for spread sheet creation benchmarks

  Mansi Uniyal, Agamdeep Singh, Ananya Singha, Priyanshu Gupta, Mukul Singh, Gust Verbruggen, Vu Le, Sumit Gulwani · 11 de agosto de 2026

  We introduce the workbook time machine, a pipeline that automatically creates benchmarks evaluating the ability of language models to create derived objects in spreadsheets (formulas, charts, pivot tables, and conditional formatting). Applied to public workbook corpora, it produces wtmcorpus--a coll…

• Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use Agents

  Siqi Fan, Minghao Li, Xiaoqian Ma, Wenhui Tan, Xiusheng Huang, Juntong Wu, Liujie Zhang, Shuo Shang, Weihang Chen · 7 de agosto de 2026

  Hybrid computer-use agents can act through screenshots or call text tools. We find that having a tool available does not settle which way the effect goes. Under one identical GUI-MCP harness on the OSWorld-MCP benchmark (309 tasks), the same MCP tools improve a reasoning model by +4.0pp and degrade …

• Plans Work in Mysterious Ways: Evaluating a Plan Mode for Spreadsheet Agents

  Aayush Kumar, Avik Dutta, Sumit Gulwani, Gustavo Soares, Advait Sarkar, Emerson Murphy-Hill · 30 de julio de 2026

  Plan Modes have become standard features in agentic programming tools, allowing users to gain transparency and control by working with the agent to develop a plan before task execution. However, it remains unclear whether the benefits of this feature translate to end-user programming environments su…

• OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding

  Jingbo Zhou, Yusai Zhao, Qi Bao, Jingjia Cao, Zhenghai Chen, Chang Gao, Kaiqi Guo, Muxin Guo, Mingxuan Li, Xinjiang Lu, Yanru Ma, Yixiong Xiao, Zenghui Zhang, Le Zhang, Hua Wu · 30 de julio de 2026

  Large language model (LLM) agents are increasingly expected to assist users in completing tasks. However, existing benchmarks provide limited support for evaluating whether agents can carry out office-suite workflows at a reasonable cost. We introduce OmegaUse-OfficeVal, a benchmark for evaluating L…

• Sheet As Token: A Graph-Enhanced Representation for Multi-Sheet Spreadsheet Understanding

  Yiming Lei, Yuhang Yao, Yujia Zhang, Yiqi Wang, Bo Guan, Depei Zhu, Chunhui Wang, Zhuonan Hao, Tianyu Shi · 29 de julio de 2026

  Workbook-scale spreadsheet understanding is increasingly important for language-model-based data analysis agents, but remains challenging because relevant information is often distributed across multiple sheets with heterogeneous schemas, layouts, and implicit relationships. Existing retrieval-augme…

• Human-in-the-Loop User Feedback Affects Perceived Accuracy and Trust, but Task Subjectivity Matters

  Donald R. Honeycutt, Mahsan Nourani, Eric D. Ragan · 21 de julio de 2026

  While ML can produce complex models beyond those that a human could produce manually, incorporating human input can often improve performance beyond purely data-driven models. While this feedback could come from system designers or domain experts, in many cases, the end users who regularly use the s…

• Where Does Agent Reliability Come From? A Cross-Benchmark Decomposition of Verification Loops, Specialist Models, and Scaffolding in a Production Enterprise Agent

  Arunabh Dastidar (for the Leni Team) · 21 de julio de 2026

  Multi-step enterprise agent tasks fail in a characteristic way: single-pass inference has no checkpoint between deciding an answer and committing to it. We study one production system (Leni) whose architecture installs such checkpoints: verification loops (execute, observe, compare, correct) staffed…

• AnovaX: A Local, Multi-Agent Voice Assistant with LLM Planning, Typed Executors, and Adaptive Recovery

  Raunak B Sinha · 20 de julio de 2026

  Desktop voice assistants are still dominated by cloud pipelines that ship raw audio off the machine and expose a fixed set of skills. We describe AnovaX, a small local-first assistant that runs entirely on the user's computer and treats the desktop itself as its action surface. A single Python proce…

• KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill

  Yunxin Li, Jinchao Li, Shibo Su, Zhenran Xu, Chenrui Zhao, Tongshu Bian, Xiaoman Liang, Meishan Zhang, Baotian Hu, Min Zhang · 15 de julio de 2026

  OpenClaw has emerged as a leading agent framework for complex task automation, yet it faces insufficient cross-platform GUI interaction support and a well-built self-evolution mechanism. These flaws limit its adaptation to diverse device ecosystems and prevent performance improvements through contin…

• Fara-1.5: Scalable Learning Environments for Computer Use Agents

  Ahmed Awadallah, Sahil Gupta, Yash Lara, Yadong Lu, Hussein Mozannar, Akshay Nambi, Zach Nussbaum, Yash Pandya, Aravind Rajeswaran, Corby Rosset, Alexey Taymanov, Luiz do Valle, Vibhav Vineet, Spencer Whitehead, Andrew Zhao · 23 de junio de 2026

  Collecting computer use data from human demonstrations is expensive and slow, motivating the need for scalable generation strategies. This requires two key ingredients: environments in which agents can act and verifiers that can judge whether their demonstrations succeeded. We introduce FaraGen1.5, …

• A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets

  Tejas Agrawal, Vu Le, Sumit Gulwani, Gust Verbruggen · 15 de junio de 2026

  Predictive code completion greatly accelerates how quickly developers work. In spreadsheets, despite being much more common, such auto-completion features are virtually non-existent. To address this gap, we introduce a benchmark for systems that observe a sequence of user actions in a spreadsheet an…

• TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning

  Mingyue Cheng, Shuo Yu, Daoyu Wang, Qingchuan Li, Xiaoyu Tao, Qingyang Mao, Yitong Zhou, Qi Liu · 10 de junio de 2026

  Spreadsheets and tables are widely used representations for structured data analysis, but effective analysis still requires substantial manual effort and domain expertise. Recent large language model (LLM) agents can automate parts of this process, but they often provide limited transparency into in…

• MBABench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance

  Thomson Yen, Julian Poeltl, Harshith Srinivas Gear, Yilin Meng, Joshua Fan, Adam Shen, Yili Liu, Ali Bauyrzhan, Siri Du, Haoyang Liu, Daniel Guetta, Hongseok Namkoong · 9 de junio de 2026

  LLM agents are increasingly expected to carry out end-to-end workflows, producing complete artifacts from high-level user instructions. To meet enterprise needs, frontier AI labs have developed agents that can construct entire spreadsheets from scratch. This is especially relevant in finance, where …

• TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration

  Soyeong Jeong, Jinheon Baek, Minki Kang, Sung Ju Hwang · 4 de junio de 2026

  Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface only the problems the user has noticed, while many other important problems coexist, hidden in plain sight, within the broader user context, with their …

• BlueFin: Benchmarking LLM Agents on Financial Spreadsheets

  Srivatsa Kundurthy, Clara Na, Colton Moraine, Anoushka Mohta, Case Winter, George Fang, John Ling, Emma Strubell, Zach Kirshner · 1 de junio de 2026

  We present BlueFin, a benchmark that tasks large language model (LLM) agents with synthesis, manipulation, and comprehension tasks over spreadsheet workbooks in the professional finance domain. Though estimates of the global population of paying users of spreadsheet software range in the hundreds of…

• Covering Human Action Space for Computer Use: Data Synthesis and Benchmark

  Miaosen Zhang, Xiaohan Zhao, Zhihong Tan, Zhou Huoshen, Yijia Fan, Yifan Yang, Kai Qiu, Bei Liu, Justin Wagle, Chenzhong Yin, Mingxi Cheng, Ji Li, Qi Dai, Chong Luo, Xu Yang, Xin Geng, Baining Guo · 13 de mayo de 2026

  Computer-use agents (CUAs) automate on-screen work, as illustrated by GPT-5.4 and Claude. Yet their reliability on complex, low-frequency interactions is still poor, limiting user trust. Our analysis of failure cases from advanced models suggests a long-tail pattern in GUI operations, where a relati…