# How Well Can AI Generate Backlogs from App Mockups?

arXiv: https://arxiv.org/abs/2607.22902 · HTML: https://mlsanity.com/paper/2607.22902/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 48 references that are in the map.
- First posted on arXiv 24 Jul 2026.

## Builds on (most cited first, 30 of 33)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [Large Language Models for Software Engineering: Survey and Open Problems](https://mlsanity.com/paper/2310.03533/) (2023)
- [Compositional Chain-of-Thought Prompting for Large Multimodal Models](https://mlsanity.com/paper/2311.17076/) (2023)
- [Structured Chain-of-Thought Prompting for Code Generation](https://mlsanity.com/paper/2305.06599/) (2023)
- [ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design](https://mlsanity.com/paper/2303.07839/) (2023)
- [SpecGen: Automated Generation of Formal Program Specifications via Large Language Models](https://mlsanity.com/paper/2401.08807/) (2024)
- [AI-Augmented Brainwriting: Investigating the use of LLMs in group ideation](https://mlsanity.com/paper/2402.14978/) (2024)
- [Make LLM a Testing Expert: Bringing Human-like Interaction to Mobile GUI Testing via Functionality-aware Decisions](https://mlsanity.com/paper/2310.15780/) (2023)
- [A Survey on Large Language Model Hallucination via a Creativity Perspective](https://mlsanity.com/paper/2402.06647/) (2024)
- [Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach](https://mlsanity.com/paper/2406.16386/) (2024)
- [ChatCoder: Chat-based Refine Requirement Improves LLMs' Code Generation](https://mlsanity.com/paper/2311.00272/) (2023)
- [How Effective are Large Language Models in Generating Software Specifications?](https://mlsanity.com/paper/2306.03324/) (2023)
- [How Do Programming Students Use Generative AI?](https://mlsanity.com/paper/2501.10091/) (2025)
- [LLMREI: Automating Requirements Elicitation Interviews with LLMs](https://mlsanity.com/paper/2507.02564/) (2025)
- [Naming the Pain in Requirements Engineering: Contemporary Problems, Causes, and Effects in Practice](https://mlsanity.com/paper/1611.10288/) (2016)
- [Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT](https://mlsanity.com/paper/2311.11547/) (2023)
- [Automated User Story Generation with Test Case Specification Using Large Language Model](https://mlsanity.com/paper/2404.01558/) (2024)
- [PersonaGen: A Tool for Generating Personas from User Feedback](https://mlsanity.com/paper/2307.00390/) (2023)
- [Using Large Language Models for Natural Language Processing Tasks in Requirements Engineering: A Systematic Guideline](https://mlsanity.com/paper/2402.13823/) (2024)
- [Does GenAI Make Usability Testing Obsolete?](https://mlsanity.com/paper/2411.00634/) (2024)
- [Leveraging Large Vision Language Model For Better Automatic Web GUI Testing](https://mlsanity.com/paper/2410.12157/) (2024)
- [GUing: A Mobile GUI Search Engine using a Vision-Language Model](https://mlsanity.com/paper/2405.00145/) (2024)
- [On AI-Inspired UI-Design](https://mlsanity.com/paper/2406.13631/) (2024)
- [From Requirements to Code: Understanding Developer Practices in LLM-Assisted Software Engineering](https://mlsanity.com/paper/2507.07548/) (2025)
- [An Alternative Issue Tracking Dataset of Public Jira Repositories](https://mlsanity.com/paper/2201.08368/) (2022)

## Abstract (arXiv)

Creating sprint backlogs requires considerable effort, as items such as epics, user stories, and tasks can be missed or inconsistently specified. We propose a multimodal approach to support backlog generation from visual app mockups, an artifact available at early project stages. We evaluate three prompting strategies on GPT-4o: a zero-shot baseline, Compositional Chain-of-Thought (CCoT) for vision-language reasoning, and a persona-driven prompt. We study seven app development projects across two countries and interview developers about the results. Overall, we observed that the baseline prompt favours recall over precision, whereas CCoT is more balanced, achieving average F1 scores of 52-66% for epics and user stories. Tasks were more challenging to generate accurately. Precision gains were most consistent when adding architectural context, particularly for backend tasks (precision gains up to 35%). Interviews with developers revealed that up to 26% of false positives were still considered useful, reflecting the creative and open-ended nature of backlog creation. To capture this, we propose a new measure called Revised Recall, which complements ground-truth evaluation with developer assessments. Our findings suggest that hybrid prompting with architectural context can assist backlog generation from early mockups, though results vary by item type and developer oversight remains necessary.