CA2: Code-Aware Agent for Automated Game Testing

Valliappan Chidambaram Adaikkappan, Vincent Martineau, Joshua Romoff, David Meger
Proceedings of the The 39th Canadian Conference on Artificial Intelligence, PMLR 318:89-102, 2026.

Abstract

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 \okey  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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v318-adaikkappan26a, title = {CA2: Code-Aware Agent for Automated Game Testing}, author = {Adaikkappan, Valliappan Chidambaram and Martineau, Vincent and Romoff, Joshua and Meger, David}, booktitle = {Proceedings of the The 39th Canadian Conference on Artificial Intelligence}, pages = {89--102}, year = {2026}, editor = {Bouzar-Benlabiod, Lydia and Leung, Carson}, volume = {318}, series = {Proceedings of Machine Learning Research}, month = {25--29 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v318/main/assets/adaikkappan26a/adaikkappan26a.pdf}, url = {https://proceedings.mlr.press/v318/adaikkappan26a.html}, abstract = {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 \okey  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.} }
Endnote
%0 Conference Paper %T CA2: Code-Aware Agent for Automated Game Testing %A Valliappan Chidambaram Adaikkappan %A Vincent Martineau %A Joshua Romoff %A David Meger %B Proceedings of the The 39th Canadian Conference on Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Lydia Bouzar-Benlabiod %E Carson Leung %F pmlr-v318-adaikkappan26a %I PMLR %P 89--102 %U https://proceedings.mlr.press/v318/adaikkappan26a.html %V 318 %X 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 \okey  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.
APA
Adaikkappan, V.C., Martineau, V., Romoff, J. & Meger, D.. (2026). CA2: Code-Aware Agent for Automated Game Testing. Proceedings of the The 39th Canadian Conference on Artificial Intelligence, in Proceedings of Machine Learning Research 318:89-102 Available from https://proceedings.mlr.press/v318/adaikkappan26a.html.

Related Material