GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning

Jiajun Chen(SII), Shicheng Fang, Jiahao Lu, Yuxin Wang, Xipeng Qiu

GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning: 12 upvotes on Hugging Face Daily Papers, #7 of 21 papers on 2026-11-12. Day-by-day upvote history.

Upvotes over time

It had 12 upvotes by its first day, 12 upvotes by the next day, 12 upvotes by day 3, 12 upvotes by day 7, and has 12 now. It ranked #50 of 133 papers in its week and #148 of 340 in its month. Its code repository has 10 GitHub stars.

AAA games offer a rich testbed for evaluating agent perception, reasoning, and control. However, evaluating whether agents can complete tasks in AAA games is challenging and often human-annotated because task outcomes are often difficult to verify automatically, let alone applying it for Reinforcement Learning (RL). We introduce GTAGym, an environment and framework for evaluation and RL on GTA V tasks. Its evaluation benchmark, GTAVBench, derived from GTA V main-story missions, contains 103 online tasks reconstructed across nine task families, alongside 47 image-based shooting and sniping tasks using GTA V imagery. A web server provides access to the online environment and evaluation interface, supporting parallel testing through screenshots and keyboard-mouse actions with automatic engine-state outcome checks. We evaluate six frontier LLMs on GTAVBench with textual task instructions and on its GTAVBench-AGI branch, where instructions appear only in the first screenshot and a harness automatically compresses interaction history. The best configuration achieves 70.9% overall accuracy in GTAVBench-AGI, yet aerial navigation, evasion and interception remain difficult. GTAGym also provides a scalable generator that samples task parameters within user-specified ranges and option sets under fixed templates, creating batches of 3D and image-based shooting environments for RL with automatic reward and termination signals. LoRA RL of Qwen3.8-27B on generated on-foot navigation tasks improves the in-domain performance and transfers to out-of-domain task categories, and native GTA V tasks from 15% to 23%.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.