SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL

SpaceTools empowers VLMs with vision and robotic tools for spatial reasoning via Double Interactive Reinforcement Learning (DIRL), enabled by our Toolshed infrastructure. Achieves state-of-the-art performance on spatial reasoning benchmarks and enables precise real-world robot manipulation.

关键词：vision language models, spatial reasoning, reinforcement learning, robotics, computer vision, tool-augmented AI