SOURCE-LINKED INTELLIGENCE

JustMem: Just-Enough Memory Access for Long-Term Conversations

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Efficient long-term conversational memory requires retrieving sufficient evidence without indiscriminately expanding the context presented to the language model. This is challenging because relevant evidence may be distributed across multiple sessions, while compression may discard details needed for answering. Different queries therefore require different forms of memory access. To capture these demands, we formulate memory access along two dimensions: discovery breadth, which controls how broadly evidence is searched, and reading fidelity, which controls whether evidence is read in compact f

Read original source ↗ Open in workspace

recordType

paper

region

Global