SOURCE-LINKED INTELLIGENCE

When Memory Takes Gradients: Collaborative Vector Memory for Agentic Recommender Systems

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Agentic recommender systems ground each decision of a large language model (LLM) in a persistent memory of the user, and in existing agents that memory is text: a narrative written and maintained by further LLM calls. Text limits this memory in two ways. It is updated one rewrite at a time, so exploiting the full interaction history is prohibitively expensive; and collaborative evidence, graded similarity over an entire catalog, does not survive translation into sentences. We propose CoVeMem (Collaborative Vector Memory), which vectorizes the collaborative core of the agent's memory. Frozen Li

Read original source ↗ Open in workspace

recordType

paper

region

Global