research
Memory Became a Query-Shaped Forest
GraphMemix builds a relevant evidence subgraph at query time instead of summarizing every memory in advance.
Summary
GraphMemix builds a relevant evidence subgraph at query time instead of summarizing every memory in advance.
The method expands seed memories through semantic and schema relations, prices evidence and activation costs, and selects a forest under a fixed budget. Across four long-term multimodal-memory benchmarks, the authors report a new accuracy-versus-lifecycle-cost frontier. The gains depend on the evaluated datasets and foundation models rather than proving universal memory reliability.
Why it matters
GraphMemix builds a relevant evidence subgraph at query time instead of summarizing every memory in advance.
Limits and context
No additional limitation was separately recorded.
Key claims
GraphMemix builds a relevant evidence subgraph at query time instead of summarizing every memory in advance.
Evidence: source-2026-08-28-016
Sources
- arXiv preprint 2608.26983arXiv · primary research
Corrections
No corrections have been recorded for this story.