Researchers from King's College London and The Alan Turing Institute introduce xMemory, a hierarchical memory management system that reduces AI agent token usage from over 9,000 to approximately 4,700 tokens per query.
xMemory introduces a four-level semantic hierarchy that cuts AI agent token usage nearly in half, promising to revolutionize long conversation and multi-session AI task handling.
Researchers from King's College London and The Alan Turing Institute have developed xMemory, a new memory architecture that cuts token usage by nearly 50% while improving AI response quality.
Researchers from King's College London and The Alan Turing Institute introduce xMemory, a hierarchical memory management system that reduces AI agent token usage from over 9,000 to approximately 4,700 tokens per query.
Researchers from King's College London and The Alan Turing Institute have developed xMemory, a hierarchical memory system that slashes AI agent token usage by nearly 50% — without any accuracy loss. Here's…
