SheetAlign: Grounded Interaction and Stage-Isolated Learning for Spreadsheet Agents
Organizations: The University of Melbourne
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.
Figures & tables
| Method | Avg. (%) | ||
|---|---|---|---|
| Closed-source systems | |||
| GPT-4o (LibreOffice) | 16.8 | ||
| GPT-4o (Excel) | 18.4 | ||
| OpenAI o3 | 23.3 | ||
| ChatGPT Agent | 35.3 | ||
| ChatGPT Agent (.xlsx) | 45.5 | ||
| Spreadsheet-RL | SheetAlign | ||||
|---|---|---|---|---|---|
| Domain | Base | RL | Harness | Learn. | Consist. |
| Finance-B | 15.6 | 29.3 | 36.7 | 37.0 | 42.9 |
| Finance-I | 7.7 | 16.2 | 26.8 | 28.1 | 31.2 |
| Finance-A | 8.1 | 19.3 | 22.2 | 27.4 | 28.8 |
| Supply Chain | 1.1 | 5.0 | 10.6 | 14.4 | 16.0 |
| HR | 0.5 | 3.2 | 13.5 | 14.1 | 14.6 |
| SpreadsheetBench | |||
|---|---|---|---|
| Configuration | Hard | Avg. | Exec. |
| Full interface | 23.9 | 29.2 | 97.1 |
| w/o task-guided inspection | 17.2 | 21.4 | 96.7 |
| w/o API grounding | 20.7 | 25.2 | 95.8 |
| w/o diagnostic repair | 20.2 | 24.4 | 90.5 |
| Domain-Spreadsheet | |||
| SpreadsheetBench | Domain | ||||
| Configuration | Hard | Avg. | Exec. | Avg. | Exec. |
| Training signals | |||||
| Outcome-based | 24.0 | 29.1 | 95.7 | 22.3 | 90.8 |
| Common (multi-signal) | 24.5 | 29.3 | 96.4 | 24.0 | 92.5 |
| Stage-isolated training | |||||
| Generation + Common | 24.9 | 30.0 | 97.0 | 25.3 | 92.7 |
| SpreadsheetBench | ||||
| Candidate pool | Selection | Hard | Avg. | Exec. |
| Common + Generation | First-valid | 25.0 | 30.7 | 98.2 |
| Common + Generation | Learned | 25.8 | 31.4 | 98.4 |
| Grounded task interface | Consistency | 26.1 | 31.5 | 98.2 |
| Common policy | Consistency | 26.6 | 32.4 | 98.6 |
| Generation policy | Consistency | 26.8 | 32.7 | 98.5 |
| Benchmark | Selected | Oracle | Gap |
|---|---|---|---|
| SpreadsheetBench | 32.8 | 39.7 | 6.9 |
| Domain-Spreadsheet | 30.1 | 40.7 | 10.6 |
Appendix figures & tables2 assets
Supplementary material from the paper’s appendix.
Appendix
| Setting | Value |
|---|---|
| Optimizer updates | 40 |
| Prompts per update | 4 |
| Responses per prompt ( ) | 4 |
| Learning rate | |
| LoRA rank | 16 |
| LoRA scaling parameter | 32 |
Spreadsheet Automation
Spreadsheet automation uses AI to understand, create, edit, and validate workbooks while preserving their formulas, structure, and intended use.
See all 23 papers