# Choose Your Own Adventure: Non-Linear AI-Assisted Programming with EvoGraph

arXiv: https://arxiv.org/abs/2604.18883 · HTML: https://mlsanity.com/paper/2604.18883/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 63 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 21 of 21)

- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing](https://mlsanity.com/paper/2309.09128/) (2023)
- [On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub](https://mlsanity.com/paper/2509.14745/) (2025)
- [Investigating Explainability of Generative AI for Code through Scenario-based Design](https://mlsanity.com/paper/2202.04903/) (2022)
- [Using AI-Based Coding Assistants in Practice: State of Affairs, Perceptions, and Ways Forward](https://mlsanity.com/paper/2406.07765/) (2024)
- [Need Help? Designing Proactive AI Assistants for Programming](https://mlsanity.com/paper/2410.04596/) (2024)
- [Perfection Not Required? Human-AI Partnerships in Code Translation](https://mlsanity.com/paper/2104.03820/) (2021)
- [Investigating and Designing for Trust in AI-powered Code Generation Tools](https://mlsanity.com/paper/2305.11248/) (2023)
- [Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support](https://mlsanity.com/paper/2502.18658/) (2025)
- [Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions](https://mlsanity.com/paper/2302.07248/) (2023)
- [Examining the Use and Impact of an AI Code Assistant on Developer Productivity and Experience in the Enterprise](https://mlsanity.com/paper/2412.06603/) (2024)
- [Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations](https://mlsanity.com/paper/2401.04883/) (2024)
- [Ivie: Lightweight Anchored Explanations of Just-Generated Code](https://mlsanity.com/paper/2403.02491/) (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)
- [A Study on Developer Behaviors for Validating and Repairing LLM-Generated Code Using Eye Tracking and IDE Actions](https://mlsanity.com/paper/2405.16081/) (2024)
- [Accountability in Code Review: The Role of Intrinsic Drivers and the Impact of LLMs](https://mlsanity.com/paper/2502.15963/) (2025)
- [OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models](https://mlsanity.com/paper/2508.21061/) (2025)
- [Natural Language Processing for Requirements Traceability](https://mlsanity.com/paper/2405.10845/) (2024)
- [Correlates of Programmer Efficacy and Their Link to Experience: A Combined EEG and Eye-Tracking Study](https://mlsanity.com/paper/2303.07071/) (2023)
- [InterLink: Linking Text with Code and Output in Computational Notebooks](https://mlsanity.com/paper/2502.16114/) (2025)

## Abstract (arXiv)

Current AI-assisted programming tools are predominantly linear and chat-based, which deviates from the iterative and branching nature of programming itself. Our preliminary study with developers using AI assistants suggested that they often struggle to explore alternatives, manage prompting sequences, and trace changes. Informed by these insights, we created EvoGraph, an IDE plugin that integrates AI interactions and code changes as a lightweight and interactive development graph. EvoGraph automatically records a branching AI-assisted coding history and allows developers to manipulate the graph to compare, merge, and revisit prior collaborative AI programming states. Our user study with 20 participants revealed that EvoGraph addressed developers' challenges identified in our preliminary study while imposing lower cognitive load. Participants also found the graph-based representation supported safe exploration, efficient iteration, and reflection on AI-generated changes. Our work highlights design opportunities for tools to help developers make sense of and act on their problem-solving progress in the emerging AI-mediated programming context.