# CA2: Code-Aware Agent for Automated Game Testing

arXiv: https://arxiv.org/abs/2605.13918 · HTML: https://mlsanity.com/paper/2605.13918/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 33 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 26 of 26)

- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos](https://mlsanity.com/paper/2206.11795/) (2022)
- [Learning Latent Plans from Play](https://mlsanity.com/paper/1903.01973/) (2019)
- [Benchmarking the Spectrum of Agent Capabilities](https://mlsanity.com/paper/2109.06780/) (2021)
- [STEVE-1: A Generative Model for Text-to-Behavior in Minecraft](https://mlsanity.com/paper/2306.00937/) (2023)
- [Scaling Instructable Agents Across Many Simulated Worlds](https://mlsanity.com/paper/2404.10179/) (2024)
- [CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents](https://mlsanity.com/paper/2401.10568/) (2024)
- [Augmenting Automated Game Testing with Deep Reinforcement Learning](https://mlsanity.com/paper/2103.15819/) (2021)
- [Improving Playtesting Coverage via Curiosity Driven Reinforcement Learning Agents](https://mlsanity.com/paper/2103.13798/) (2021)
- [A Survey of Video Game Testing](https://mlsanity.com/paper/2103.06431/) (2021)
- [Technical Challenges of Deploying Reinforcement Learning Agents for Game Testing in AAA Games](https://mlsanity.com/paper/2307.11105/) (2023)
- [Automated Play-Testing Through RL Based Human-Like Play-Styles Generation](https://mlsanity.com/paper/2211.17188/) (2022)
- [GLIB: Towards Automated Test Oracle for Graphically-Rich Applications](https://mlsanity.com/paper/2106.10507/) (2021)
- [Inspector: Pixel-Based Automated Game Testing via Exploration, Detection, and Investigation](https://mlsanity.com/paper/2207.08379/) (2022)
- [Leveraging LLM Agents for Automated Video Game Testing](https://mlsanity.com/paper/2509.22170/) (2025)
- [Godot Reinforcement Learning Agents](https://mlsanity.com/paper/2112.03636/) (2021)
- [Robust Imitation Learning for Automated Game Testing](https://mlsanity.com/paper/2401.04572/) (2024)

## Abstract (arXiv)

Automated game testing is important for verifying game functionality, but it remains a costly and time-consuming process. Manual testing often misses edge cases, and current automated methods struggle to provide full code coverage. Prior work has explored reinforcement learning (RL) for game testing, but without leveraging internal code signals such as the call stack. We present Code Aware Agent (CA2), which uses call stack information to learn effective testing strategies. The agent receives the current function call trace along with the game state and learns to reach specific target functions. We instrument two types of environments, 1) State-based and 2) Image-based, with support for efficient call stack extraction. Through experimental evaluation, we find that CA2 achieves consistent improvement over the non-code aware baselines, which does not leverage call stack information. Our results show that incorporating code signals like the call stack enables more effective and targeted game testing.