# JointCore preprint reports fewer queries to select AI agent memories

_Published Monday, October 19, 2026 at 6:47 AM EDT · Science, AI · Latest · Tier 2 — Notable_

Researchers report in an arXiv preprint that JointCore, a method for selecting which memory records an AI agent needs, reduced model queries while preserving full-memory behavior in benchmark tests. Across four model families with 12B-70B parameters and 432 tasks per model, it averaged 10.28 queries versus 16.00 for a method that removes individual records, with minimum-cost recovery of 50.6% versus 43.1%.

JointCore tests groups of records before individual entries, addressing evidence that is redundant or useful only in combination. The researchers also introduced JointCoreBench, which supplies exact sufficient-set answers across nine interaction families and six workflow domains. Behavior preservation depended on the deterministic primary interface; alternative interfaces produced different behavior. The study does not establish deployment-ready memory compression.

## Sources

- [cs.LG updates on arXiv.org](https://arxiv.org/abs/2610.23266)

---
Canonical: https://techandbusiness.org/newswire/ZSaUggT3eRIygUrcWqqVfa
Published: 2026-10-19T10:47:45.659Z
Story chronology: 2026-10-19T04:00:00.000Z
Retrieved: 2026-10-19T13:18:13.624Z
Publisher: Tech & Business (techandbusiness.org)