# Plans Work in Mysterious Ways: Evaluating a Plan Mode for Spreadsheet Agents

arXiv: https://arxiv.org/abs/2607.23670 · HTML: https://mlsanity.com/paper/2607.23670/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 48 references that are in the map.
- First posted on arXiv 26 Jul 2026.

## 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, 23 of 23)

- [Does Writing with Language Models Reduce Content Diversity?](https://mlsanity.com/paper/2309.05196/) (2023)
- [CodePlan: Repository-level Coding using LLMs and Planning](https://mlsanity.com/paper/2309.12499/) (2023)
- [SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models](https://mlsanity.com/paper/2305.19308/) (2023)
- [Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistant](https://mlsanity.com/paper/2502.01390/) (2025)
- ["What It Wants Me To Say": Bridging the Abstraction Gap Between End-User Programmers and Code-Generating Large Language Models](https://mlsanity.com/paper/2304.06597/) (2023)
- [Magentic-UI: Towards Human-in-the-loop Agentic Systems](https://mlsanity.com/paper/2507.22358/) (2025)
- [What is it like to program with artificial intelligence?](https://mlsanity.com/paper/2208.06213/) (2022)
- [Cocoa: Co-Planning and Co-Execution with AI Agents](https://mlsanity.com/paper/2412.10999/) (2024)
- [Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decomposition](https://mlsanity.com/paper/2407.02651/) (2024)
- [SheetAgent: Towards A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models](https://mlsanity.com/paper/2403.03636/) (2024)
- [Beyond Code Generation: LLM-supported Exploration of the Program Design Space](https://mlsanity.com/paper/2503.06911/) (2025)
- [BISCUIT: Scaffolding LLM-Generated Code with Ephemeral UIs in Computational Notebooks](https://mlsanity.com/paper/2404.07387/) (2024)
- [AI, Help Me Thinkunicodex2014but for Myself: Assisting People in Complex Decision-Making by Providing Different Kinds of Cognitive Support](https://mlsanity.com/paper/2504.06771/) (2025)
- [AI Should Challenge, Not Obey](https://mlsanity.com/paper/2411.02263/) (2024)
- [Why AI Agents Still Need You: Findings from Developer-Agent Collaborations in the Wild](https://mlsanity.com/paper/2506.12347/) (2025)
- [Understanding, Protecting, and Augmenting Human Cognition with Generative AI: A Synthesis of the CHI 2025 Tools for Thought Workshop](https://mlsanity.com/paper/2508.21036/) (2025)
- ["It's like a rubber duck that talks back": Understanding Generative AI-Assisted Data Analysis Workflows through a Participatory Prompting Study](https://mlsanity.com/paper/2407.02903/) (2024)
- [TableTalk: Scaffolding Spreadsheet Development with a Language Agent](https://mlsanity.com/paper/2502.09787/) (2025)
- [Dango: A Mixed-Initiative Data Wrangling System using Large Language Model](https://mlsanity.com/paper/2503.03154/) (2025)
- [Will Code Remain a Relevant User Interface for End-User Programming with Generative AI Models?](https://mlsanity.com/paper/2311.00382/) (2023)
- [Dynamic Prompt Middleware: Contextual Prompt Refinement Controls for Comprehension Tasks](https://mlsanity.com/paper/2412.02357/) (2024)
- [The Invisible Mentor: Inferring User Actions from Screen Recordings to Recommend Better Workflows](https://mlsanity.com/paper/2509.26557/) (2025)
- [From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering](https://mlsanity.com/paper/2512.23844/) (2025)

## Abstract (arXiv)

Plan Modes have become standard features in agentic programming tools, allowing users to gain transparency and control by working with the agent to develop a plan before task execution. However, it remains unclear whether the benefits of this feature translate to end-user programming environments such as spreadsheets. Since spreadsheet programmers tend to work iteratively and care less about technical correctness, upfront planning may not fit into their workflows as easily. In this paper, we build a prototype of a Plan Mode for spreadsheet programming and evaluate it against a non-planning baseline through a within-subjects user study (N=24). We found that despite similar task outcomes with both tools, using Plan Mode led to a reduction in refinement and a better perception of the tool across dimensions of creativity support and human-machine collaboration. We discuss the implications of these results for the future design of Plan Modes, and for the broader role of human-AI planning in end-user programming.