# LikeThis! Empowering App Users to Submit UI Improvement Suggestions Instead of Complaints

arXiv: https://arxiv.org/abs/2603.04245 · HTML: https://mlsanity.com/paper/2603.04245/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 84 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 27 of 27)

- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [Diffusion Model-Based Image Editing: A Survey](https://mlsanity.com/paper/2402.17525/) (2024)
- [Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration](https://mlsanity.com/paper/2406.01014/) (2024)
- [LayoutDM: Discrete Diffusion Model for Controllable Layout Generation](https://mlsanity.com/paper/2303.08137/) (2023)
- [Make LLM a Testing Expert: Bringing Human-like Interaction to Mobile GUI Testing via Functionality-aware Decisions](https://mlsanity.com/paper/2310.15780/) (2023)
- [Learning to Denoise Raw Mobile UI Layouts for Improving Datasets at Scale](https://mlsanity.com/paper/2201.04100/) (2022)
- [UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback](https://mlsanity.com/paper/2406.07739/) (2024)
- [UICrit: Enhancing Automated Design Evaluation with a UICritique Dataset](https://mlsanity.com/paper/2407.08850/) (2024)
- [GUIComp: A GUI Design Assistant with Real-Time, Multi-Faceted Feedback](https://mlsanity.com/paper/2001.05684/) (2020)
- [Misty: UI Prototyping Through Interactive Conceptual Blending](https://mlsanity.com/paper/2409.13900/) (2024)
- [Automatically Matching Bug Reports With Related App Reviews](https://mlsanity.com/paper/2102.07134/) (2021)
- [Release early, release often, and watch your users' emotions](https://mlsanity.com/paper/1906.06403/) (2019)
- [GANSpiration: Balancing Targeted and Serendipitous Inspiration in User Interface Design with Style-Based Generative Adversarial Network](https://mlsanity.com/paper/2203.03827/) (2022)
- [On the Automated Processing of User Feedback](https://mlsanity.com/paper/2407.15519/) (2024)
- [Does GenAI Make Usability Testing Obsolete?](https://mlsanity.com/paper/2411.00634/) (2024)
- [Where is Your App Frustrating Users?](https://mlsanity.com/paper/2204.09310/) (2022)
- [Agent for User: Testing Multi-User Interactive Features in TikTok](https://mlsanity.com/paper/2504.15474/) (2025)
- [Extracting and Analyzing Context Information in User-Support Conversations on Twitter](https://mlsanity.com/paper/1907.13395/) (2019)
- [Unsupervised Topic Discovery in User Comments](https://mlsanity.com/paper/2108.08543/) (2021)
- [Listening to Users' Voice: Automatic Summarization of Helpful App Reviews](https://mlsanity.com/paper/2210.06235/) (2022)
- [GUing: A Mobile GUI Search Engine using a Vision-Language Model](https://mlsanity.com/paper/2405.00145/) (2024)
- [LLM-Cure: LLM-based Competitor User Review Analysis for Feature Enhancement](https://mlsanity.com/paper/2409.15724/) (2024)
- [Leveraging Encoder-only Large Language Models for Mobile App Review Feature Extraction](https://mlsanity.com/paper/2408.01063/) (2024)

## Abstract (arXiv)

User feedback is crucial for the evolution of mobile apps. However, research suggests that users tend to submit uninformative, vague, or destructive feedback. Unlike recent AI4SE approaches that focus on generating code and other development artifacts, our work aims at empowering users to submit better and more constructive UI feedback with concrete suggestions on how to improve the app. We propose LikeThis!, a GenAI-based approach that takes a user comment with the corresponding screenshot to immediately generate multiple improvement alternatives, from which the user can easily choose their preferred option. To evaluate LikeThis!, we first conducted a model benchmarking study based on a public dataset of carefully critiqued UI designs. The results show that GPT-Image-1 significantly outperformed three other state-of-the-art image generation models in improving the designs to address UI issues while keeping the fidelity and without introducing new issues. An intermediate step in LikeThis! is to generate a solution specification before sketching the design as a key to achieving effective improvement. Second, we conducted a user study with 10 production apps, where 15 users used LikeThis! to submit their feedback on encountered issues. Later, the developers of the apps assessed the understandability and actionability of the feedback with and without generated improvements. The results show that our approach helps generate better feedback from both user and developer perspectives, paving the way for AI-assisted user-developer collaboration.