- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes WUIDGET, a gap-driven post-training framework for text-to-web-UI generation. It distills evaluation failures into a structured root-cause taxonomy to guide data and reward design across three stages: SFT, RFT-D, and RL. Experiments on Qwen3-8B and SmolLM-3B across different benchmarks show improvements, supporting the effectiveness of these stages. The method also shows improvements over AesCoder-4B.
Critical strengths
- Strong overall performance across three benchmarks and two model families, Qwen3-8B and SmolLM-3B. Qwen3-8B also improves over the comparably sized AesCoder-4B by 4.18 points in static quality.
- The stage contributions are carefully analyzed. Adding RFT-D changes the outcome of subsequent RL.
Critical weaknesses
- Support for the central gap-driven claim is not strong enough. Although the paper emphasizes gap-driven training, the contribution of gap guidance is not fully isolated and validated. The improvements may depend more on the overall training recipe.
Questions for authors
How do the existing experiments independently establish the contribution of gap guidance?