Choose Your Own Adventure: Non-Linear AI-Assisted Programming with EvoGraph
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910152481832960 |
|---|---|
| author | Exarhakos, Vassilios Cheng, Jinghui Guo, Jin L. C. |
| author_facet | Exarhakos, Vassilios Cheng, Jinghui Guo, Jin L. C. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18883 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Choose Your Own Adventure: Non-Linear AI-Assisted Programming with EvoGraph Exarhakos, Vassilios Cheng, Jinghui Guo, Jin L. C. Human-Computer Interaction Artificial Intelligence Software Engineering 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. |
| title | Choose Your Own Adventure: Non-Linear AI-Assisted Programming with EvoGraph |
| topic | Human-Computer Interaction Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2604.18883 |