# TableTalk: Scaffolding Spreadsheet Development with a Language Agent

arXiv: https://arxiv.org/abs/2502.09787 · HTML: https://mlsanity.com/paper/2502.09787/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 41 of its 96 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 30 of 41)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [REFINER: Reasoning Feedback on Intermediate Representations](https://mlsanity.com/paper/2304.01904/) (2023)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [Language Models as Agent Models](https://mlsanity.com/paper/2212.01681/) (2022)
- [A Survey of Deep Learning for Mathematical Reasoning](https://mlsanity.com/paper/2212.10535/) (2022)
- [Programming Is Hard -- Or at Least It Used to Be: Educational Opportunities And Challenges of AI Code Generation](https://mlsanity.com/paper/2212.01020/) (2022)
- [Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming](https://mlsanity.com/paper/2210.14306/) (2022)
- [The Metacognitive Demands and Opportunities of Generative AI](https://mlsanity.com/paper/2312.10893/) (2023)
- [A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges](https://mlsanity.com/paper/2303.17125/) (2023)
- ["It's Weird That it Knows What I Want": Usability and Interactions with Copilot for Novice Programmers](https://mlsanity.com/paper/2304.02491/) (2023)
- [Comparing Code Explanations Created by Students and Large Language Models](https://mlsanity.com/paper/2304.03938/) (2023)
- [How Novices Use LLM-Based Code Generators to Solve CS1 Coding Tasks in a Self-Paced Learning Environment](https://mlsanity.com/paper/2309.14049/) (2023)
- [Sensecape: Enabling Multilevel Exploration and Sensemaking with Large Language Models](https://mlsanity.com/paper/2305.11483/) (2023)
- ["We Need Structured Output": Towards User-centered Constraints on Large Language Model Output](https://mlsanity.com/paper/2404.07362/) (2024)
- [Need Help? Designing Proactive AI Assistants for Programming](https://mlsanity.com/paper/2410.04596/) (2024)
- [SpreadsheetCoder: Formula Prediction from Semi-structured Context](https://mlsanity.com/paper/2106.15339/) (2021)
- [Cocoa: Co-Planning and Co-Execution with AI Agents](https://mlsanity.com/paper/2412.10999/) (2024)
- [TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Data](https://mlsanity.com/paper/2106.03096/) (2021)
- [Towards Unified Dialogue System Evaluation: A Comprehensive Analysis of Current Evaluation Protocols](https://mlsanity.com/paper/2006.06110/) (2020)
- [Investigating and Designing for Trust in AI-powered Code Generation Tools](https://mlsanity.com/paper/2305.11248/) (2023)

## Built on by (most cited first, 5 of 5)

- [Understanding User Experiences of Computer Use Agents: Design Space and Opportunities for Building Agent UX Prototypes](https://mlsanity.com/paper/2510.04452/) (2025)
- [Auditing and Controlling AI Agent Actions in Spreadsheets](https://mlsanity.com/paper/2604.20070/) (2026)
- [Automating Complex Document Workflows via Stepwise and Rollback-Enabled Operation Orchestration](https://mlsanity.com/paper/2512.04445/) (2025)
- [A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets](https://mlsanity.com/paper/2606.13802/) (2026)
- [Plans Work in Mysterious Ways: Evaluating a Plan Mode for Spreadsheet Agents](https://mlsanity.com/paper/2607.23670/) (2026)

## Abstract (arXiv)

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 agents that observe, plan, and perform tasks, showing promise for spreadsheet creation. We present TableTalk, a spreadsheet programming agent embodying three design principles -- scaffolding, flexibility, and incrementality -- derived from studies with seven spreadsheet programmers and 85 Excel templates. TableTalk guides programmers through structured plans based on professional workflows, generating three potential next steps to adapt plans to programmer needs. It uses pre-defined tools to generate spreadsheet components and incrementally build spreadsheets. In a study with 20 programmers, TableTalk produced higher-quality spreadsheets 2.3 times more likely to be preferred than the baseline. It reduced cognitive load and thinking time by 12.6%. From this, we derive design guidelines for agentic spreadsheet programming tools and discuss implications on spreadsheet programming, end-user programming, AI-assisted programming, and human-agent collaboration.