Search papers, labs, and topics across Lattice.
The paper introduces Hierarchical Memory Orchestration (HMO), a three-tiered memory system for personalized agents that prioritizes user-centric contextual relevance to mitigate performance bottlenecks associated with long-term memory. HMO uses a compact primary cache coupled with an evolving user profile, a high-priority secondary layer, and a global archive to surface relevant historical knowledge efficiently. Evaluations on multiple benchmarks and real-world deployments demonstrate state-of-the-art performance and enhanced agent fluidity and personalization.
Personalized agents can now maintain consistent historical awareness without performance bottlenecks, thanks to a hierarchical memory system that dynamically prioritizes user-relevant information.
While long-term memory is essential for intelligent agents to maintain consistent historical awareness, the accumulation of extensive interaction data often leads to performance bottlenecks. Naive storage expansion increases retrieval noise and computational latency, overwhelming the reasoning capacity of models deployed on constrained personal devices. To address this, we propose Hierarchical Memory Orchestration (HMO), a framework that organizes interaction history into a three-tiered directory driven by user-centric contextual relevance. Our system maintains a compact primary cache, coupling recent and pivotal memories with an evolving user profile to ensure agent reasoning remains aligned with individual behavioral traits. This primary cache is complemented by a high-priority secondary layer, both of which are managed within a global archive of the full interaction history. Crucially, the user persona dictates memory redistribution across this hierarchy, promoting records mapped to long-term patterns toward more active tiers while relegating less relevant information. This targeted orchestration surfaces historical knowledge precisely when needed while maintaining a lean and efficient active search space. Evaluations on multiple benchmarks achieve state-of-the-art performance. Real-world deployments in ecosystems like OpenClaw demonstrate that HMO significantly enhances agent fluidity and personalization.
Google Research