InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain 文章

ArXiv CS.AI2026-06-03NEWSen作者: Tiancheng Han, Yong Li, Wuzhou Yu, Qiaosheng Zhang, Wenqi Shao
查看原文 →
关系图谱

InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain · 相关技术

相关技术

RL-based chunk-wise agentsChunk-wise memory agentsLLMInfoMem