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

ArXiv CS.CL2026-05-29NEWSen作者: Encheng Su, Jinouwen Zhang, Jianyu Wu, Qiucheng Yu, Chen Tang, Pengze Li, Lintao Wang, Yizhou Wang, Xinzhu Ma, Shixiang Tang, Aoran Wang

摘要

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-augmented generation (RAG), systems often retrieve locally relevant but chain-incomplete evidence, especially for spatial, temporal, repeated-event, and multi-hop state questions. We propose S3MEM, a structured scene-event episodic memory framework for long-horizon interactive question answering (QA). S3MEM writes trajectories into structured memory units, retrieves evidence through anchor-sensitive retrieval, and exposes a compact token-budget-aware evidence interface for answer-time inference.

相关公司

暂无数据

相关人物

暂无数据

相关技术查看全部 (1)