S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering 事件

S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering arXiv:2605.28831v1 Announce Type: new Abstract: Long-horizon interactive agents often accumulate large trajectory histories yet still fail to answer questions about earlier events reliably. We argue that the main bottleneck is not context length alone, but the trajectory-to-answer interface of long-term memory. When histories are stored as plain-text chunks and queried with standard retrieval-aug