PlayCoder: Making LLM-Generated GUI Code Playable

TL;DR

PlayCoder introduces a multi-agent framework that enhances the generation and correctness of GUI applications by iteratively repairing code, addressing the limitations of current LLMs in producing logically consistent GUI programs.

Contribution

The paper presents PlayCoder, a novel framework that improves LLM-generated GUI code through iterative repair and evaluation, supported by a new benchmark and evaluation metric.

Findings

LLMs achieve near-zero Play@3 on GUI tasks without repair.

PlayCoder significantly improves correctness, reaching up to 38.1% Exec@3.

Traditional metrics miss silent logic bugs that PlayCoder can detect and fix.

Abstract

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.