Memory Depth and Reconstructed Context Width: A Controlled Evaluation of Hierarchical Retrieval

Excerpt

arXiv:2610.08300v1 Announce Type: new Abstract: Long-term conversational memory is becoming an integral component of modern LLM systems. Proposed architectures group records by topics and events, construct hierarchies and graphs, and connect facts through causal and temporal relations. We experimentally study the interaction between two memory parameters: structural depth and the width of context supplied to the answer model. Using EverMemBench, we evaluate depths D1-D4, core budgets of 1,024/2,