直觉与证据：多模态智能体的自适应双记忆框架
原标题：Intuition with Evidence: Adaptive Dual Memory for Multimodal Agents
AI 摘要
该论文提出一种面向多模态智能体的双记忆框架，将模型原生的潜在记忆作为直觉先验，与多索引情景记忆结合，通过检索条件联合对齐实现精确证据重建。推理时框架借助基于Jensen-Shannon散度敏感度和置信度代理的无训练路由机制，按查询自适应组合两类记忆。多模态基准评测显示其整体优于单范式基线（较原始情景记忆提升4.67%），并揭示情景记忆擅长证据定位任务、潜在记忆有助于整合分散信息并补偿不完美检索。
正文节选
Intuition with Evidence: Adaptive Dual Memory for Multimodal Agents Abstract As multimodal agents engage in sustained interactions, long-term memory serves two distinct but complementary functions: fine-grained evidence recall and internalized interpretation for global understanding. Although episodic and latent memory address these demands through explicit historical records and internalized experience, neither paradigm alone can accommodate the diverse memory affinities across tasks, owing to