V izo M em: A Visual-Textual Memory Framework for Efficient Long-Horizon Reasoning
Weijie Liang · Yuanfeng SONG · Xing Chen · Caleb Chen Cao · Sirui Han · Yike Guo
摘要
Agentic systems built upon large language models (LLMs) increasingly depend on long-context modeling to support document understanding, long-term memory recall, and multi-step reasoning. However, extending context windows incurs substantial computational and memory overhead, significantly limitin...