
YW
Yuxiang Wang, Junhao Gan, Jianzhong Qi
· 1 min read
ResearcharXiv cs.CL
SheetAlign: Grounded Interaction and Stage-Isolated Learning for Spreadsheet Agents
arXiv:2611.26069v1 Announce Type: new
Abstract: Spreadsheets are widely used for data analysis and supporting decision-making. Automating spreadsheet analysis while protecting sensitive data and controlling deployment costs motivates locally deployed open-weight large language models (LLMs). Meanwhile, complex spreadsheet tasks require both task reasoning and workbook understanding, while predefined operation interfaces impose additional tool-selection and invocation demands. We introduce SheetAlign, a spreadsheet manipulation framework with stage-isolated policy learning, organized around where to operate, what to change, and how to implement transformations. Task-guided inspection and API grounding anchor code generation in workbook observations and available operations, while stage-isolated learning optimizes program generation and review using edit-progress rewards. At inference, execution consistency selects programs through agreement among workbook states. On SpreadsheetBench, our grounded task interface improves Qwen3-4B's accuracy from 13.5% to 29.2% on average without training. With learning and execution consistency, SheetAlign achieves 32.8% accuracy on average on SpreadsheetBench and 30.1% on Domain-Spreadsheet, outperforming comparable baselines. The code will be made publicly available upon publication.
Original source
This story was published by arXiv cs.CL and written by Yuxiang Wang, Junhao Gan, Jianzhong Qi. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


