GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and Reasoning

ArXi:2603.19137v1 Announce Type: new Effective embodied exploration requires agents to accumulate and retain spatial knowledge over time. However, existing scene representations, such as discrete scene graphs or static view-based snapshots, lack \textit{post-hoc re-observability}. If an initial observation misses a target, the resulting memory omission is often irrecoverable. To bridge this gap, we propose \textbf{GSMem}, a zero-shot embodied exploration and reasoning framework built upon 3D Gaussian Splatting (3