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

arXiv: https://arxiv.org/abs/2606.13802 · HTML: https://mlsanity.com/paper/2606.13802/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 25 references that are in the map.
- First posted on arXiv 11 Jun 2026.

## Builds on (most cited first, 9 of 9)

- [IntelliCode Compose: Code Generation Using Transformer](https://mlsanity.com/paper/2005.08025/) (2020)
- [SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation](https://mlsanity.com/paper/2406.14991/) (2024)
- [On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot](https://mlsanity.com/paper/2302.00438/) (2023)
- [SpreadsheetCoder: Formula Prediction from Semi-structured Context](https://mlsanity.com/paper/2106.15339/) (2021)
- [Language Models for Code Completion: A Practical Evaluation](https://mlsanity.com/paper/2402.16197/) (2024)
- [When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming](https://mlsanity.com/paper/2306.04930/) (2023)
- [Learning Next Action Predictors from Human-Computer Interaction](https://mlsanity.com/paper/2603.05923/) (2026)
- [TableTalk: Scaffolding Spreadsheet Development with a Language Agent](https://mlsanity.com/paper/2502.09787/) (2025)
- [Demonstration of CORNET: A System For Learning Spreadsheet Formatting Rules By Example](https://mlsanity.com/paper/2308.07357/) (2023)

## Abstract (arXiv)

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 and predict future actions. Two challenges are (1) the absence of edit histories in public spreadsheet corpora and (2) the complex space of spreadsheet actions (spatial, temporal, composite). To address (1), we manually curate 52 sequences of 12K actions that recreate spreadsheets from public corpora, seeded by parametrized heuristics and LLM refinement. To address (2), we propose an online evaluation that expects a prediction after each user action, accepts or rejects that prediction, updates the future actions upon acceptance, and repeats this until the target spreadsheet is obtained. We use multiple baseline predictors (including zero-shot LLMs, fine-tuned SLMs, and classical models) and analyze different properties that our benchmark teaches us, including but not limited to: properties of saved actions and false positives, efficiency, effect of user profiles, effect of triggers, and effect of context.