# PlayCoder: Making LLM-Generated GUI Code Playable

arXiv: https://arxiv.org/abs/2604.19742 · HTML: https://mlsanity.com/paper/2604.19742/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2026.

## Built on by (most cited first, 11 of 11)

- [GUI Agents for Continual Game Generation](https://mlsanity.com/paper/2605.28258/) (2026)
- [GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?](https://mlsanity.com/paper/2608.21833/) (2026)
- [Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation](https://mlsanity.com/paper/2605.30000/) (2026)
- [AI for Games in the Foundation Model Era](https://mlsanity.com/paper/2609.16679/) (2026)
- [DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents](https://mlsanity.com/paper/2605.17439/) (2026)
- [GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions](https://mlsanity.com/paper/2609.21562/) (2026)
- [WebGrader: Training LLMs for Web Development with Self-Evolving Programmatic Grader](https://mlsanity.com/paper/2608.06474/) (2026)
- [GameASG-Bench: Benchmarking Autonomous Software Generation for Game Development](https://mlsanity.com/paper/2609.21293/) (2026)
- [OpenHarmony Bench: Evaluating LLMs and Coding Agents on OpenHarmony App Development](https://mlsanity.com/paper/2608.16022/) (2026)
- [SWE-Game: Can Coding Agents Build the Games We Want?](https://mlsanity.com/paper/2609.33678/) (2026)
- [Spec2Game: Can LLMs Generate Complete Playable Games from Detailed Specifications?](https://mlsanity.com/paper/2610.04253/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have achieved strong results in code generation, but their ability to generate GUI applications, especially games, remains insufficiently studied. Existing benchmarks mainly evaluate correctness through test cases, which are inadequate for GUI applications because these systems are interactive, event-driven, and require correct state transitions across sequences of user actions. Their evaluation therefore should consider interaction flows and UI logic rather than only pass/fail outcomes. To study this problem, we introduce PlayEval, a repository-aware benchmark built from 43 multilingual GUI applications in Python, TypeScript, and JavaScript. Unlike prior GUI benchmarks that are difficult to adapt to desktop environments, PlayEval covers six major GUI application categories and directly supports code-generation evaluation. We further propose Play@k, a metric that measures whether at least one of *k* generated candidates can be played end-to-end without logical errors. To support reliable evaluation, we develop PlayTester, an LLM-based agent that performs task-oriented GUI playthroughs and detects logic violations automatically. Experiments on 10 state-of-the-art code LLMs show that, despite high compilation rates, they achieve near-zero Play@3, revealing major weaknesses in generating logically correct GUI applications. To address this limitation, we present PlayCoder, a multi-agent, repository-aware framework that generates, evaluates, and iteratively repairs GUI application code in a closed loop. PlayCoder substantially improves both functional correctness and semantic alignment for open-source and closed-source models, reaching up to 38.1% Exec@3 and 20.3% Play@3. Case studies further show that it can uncover silent logic bugs missed by traditional metrics and fix them through targeted edits.