TableTalk: Scaffolding Spreadsheet Development with a Language Agent

2025-02-13

AI Summary

Spreadsheet programming, though widespread, imposes high cognitive demands on users who must simultaneously manage domain knowledge, formula logic, and GUI interactions. To address this, we propose a human–computer collaborative conversational language agent grounded in three design principles: scaffolding, flexibility, and incrementality. Our approach introduces a novel three-stage progressive formula suggestion mechanism and a persistent, direct-manipulation interface supporting pausing and undo. Built upon large language models, the agent integrates specialized tools—including formula generation and cell-level operations—and incorporates user behavior–driven stepwise planning with real-time feedback. A user study demonstrates that, compared to baseline methods, spreadsheets generated by our agent are preferred 2.3× more frequently; users exhibit 12.6% lower cognitive load and reduced reasoning time, while also reporting significantly improved controllability and usability.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Multiagent Systems: Agent Communication

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Despite its ubiquity in the workforce, spreadsheet programming remains challenging as programmers need both spreadsheet-specific knowledge (e.g., APIs to write formulas) and problem-solving skills to create complex spreadsheets. Large language models (LLMs) can help automate aspects of this process, and recent advances in planning and reasoning have enabled language agents, which dynamically plan, use tools, and take iterative actions to complete complex tasks. These agents observe, plan, and act, making them well-suited to scaffold spreadsheet programming by following expert processes. We present TableTalk, a language agent that helps programmers build spreadsheets conversationally. Its design reifies three design principles -- scaffolding, flexibility, and incrementality -- which we derived from two studies of seven programmers and 62 Excel templates. TableTalk structures spreadsheet development by generating step-by-step plans and suggesting three next steps users can choose from. It also integrates tools that enable incremental spreadsheet construction. A user study with 20 programmers shows that TableTalk produces spreadsheets 2.3 times more likely to be preferred over a baseline agent, while reducing cognitive load and time spent reasoning about spreadsheet actions by 12.6%. TableTalk's approach has implications for human-agent collaboration. This includes providing persistent direct manipulation interfaces for stopping or undoing agent actions, while ensuring that such interfaces for accepting actions can be deactivated.

Problem

• Automates spreadsheet programming with language agents
• Reduces cognitive load in spreadsheet development
• Enhances human-agent collaboration in spreadsheet creation

Innovation

• Language agent scaffolds spreadsheet development
• Dynamic planning enhances spreadsheet programming
• Incremental tools reduce cognitive load