2 papers
cs.CL2026
WhenLoss: Diagnosing Write and Retrieval Bottlenecks in Long-Context Memory Systems
Jiangnan Yu, Kisson Songqi Lin, Jilong Wu
Long-context memory systems often fail under fixed budgets, but end-to-end evaluation does not reveal whether evidence was discarded during compression or preserved but never retri…
cs.CR2026
MemTrust: A Zero-Trust Architecture for Unified AI Memory System
Xing Zhou, Dmitrii Ustiugov, Haoxin Shang +1
AI memory systems are evolving toward unified context layers that enable efficient cross-agent collaboration and multi-tool workflows, facilitating better accumulation of personal…