# Synergizing Code Coverage and Gameplay Intent: Coverage-Aware Game Playtesting with LLM-Guided Reinforcement Learning

arXiv: https://arxiv.org/abs/2512.12706 · HTML: https://mlsanity.com/paper/2512.12706/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 37 references that are in the map.
- First posted on arXiv 14 Dec 2025.

## Builds on (most cited first, 12 of 12)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [Augmenting Automated Game Testing with Deep Reinforcement Learning](https://mlsanity.com/paper/2103.15819/) (2021)
- [Automated Playtesting with Procedural Personas through MCTS with Evolved Heuristics](https://mlsanity.com/paper/1802.06881/) (2018)
- [Improving Playtesting Coverage via Curiosity Driven Reinforcement Learning Agents](https://mlsanity.com/paper/2103.13798/) (2021)
- [Automated Video Game Testing Using Synthetic and Human-Like Agents](https://mlsanity.com/paper/1906.00317/) (2019)
- [Large Language Models are Pretty Good Zero-Shot Video Game Bug Detectors](https://mlsanity.com/paper/2210.02506/) (2022)
- [Playtesting: What is Beyond Personas](https://mlsanity.com/paper/2107.11965/) (2021)
- [Are the Old Days Gone? A Survey on Actual Software Engineering Processes in Video Game Industry](https://mlsanity.com/paper/2009.02448/) (2020)
- [An approach to automated videogame beta testing](https://mlsanity.com/paper/2402.04938/) (2024)

## Built on by (most cited first, 2 of 2)

- [GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers](https://mlsanity.com/paper/2604.02648/) (2026)
- [AI for Games in the Foundation Model Era](https://mlsanity.com/paper/2609.16679/) (2026)

## Abstract (arXiv)

The widespread adoption of the "Games as a Service" model necessitates frequent content updates, placing immense pressure on quality assurance. In response, automated game testing has been viewed as a promising solution to cope with this demanding release cadence. However, existing automated testing approaches typically create a dichotomy: code-centric methods focus on structural coverage without understanding gameplay context, while player-centric agents validate high-level intent but often fail to cover specific underlying code changes. To bridge this gap, we propose SMART (Structural Mapping for Augmented Reinforcement Testing), a novel framework that synergizes structural verification and functional validation for game update testing. SMART leverages large language models (LLMs) to interpret abstract syntax tree (AST) differences and extract functional intent, constructing a context-aware hybrid reward mechanism. This mechanism guides reinforcement learning agents to sequentially fulfill gameplay goals while adaptively exploring modified code branches. We evaluate SMART on two environments, Overcooked and Minecraft. The results demonstrate that SMART significantly outperforms state-of-the-art baselines; it achieves over 94% branch coverage of modified code, nearly double that of traditional reinforcement learning methods, while maintaining a 98% task completion rate, effectively balancing structural comprehensiveness with functional correctness.