GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning Paper • 2611.13028 • Published 3 days ago • 1
VehicleArena: A Realistic Urban Environment for Multi-Agent Driving Paper • 2609.35916 • Published Sep 28 • 3
SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science? Paper • 2608.19799 • Published Aug 20 • 63