RoBoSR: Structured Scene Representations for Embodied Robotic Reasoning

arXiv:2606.24338v1 Announce Type: new Abstract: Despite rapid progress, embodied reasoning under real-world variability remains challenging. Existing approaches rely on demonstration-driven sequential biases, limiting flexibility in open-ended and long-horizon tasks that require structured reasoning over evolving states. We introduce RoBoSR, an intermediate structural representation that formulates manipulation as step-wise state transitions over semantically grounded, object-centric scene graph...