What question did this study set out to answer?

This research introduces a federated cognitive memory architecture aimed at improving memory retrieval among agents.

May 14, 2026Open Access

Federated Cognitive Memory: Tiered Access, Semiotic Density Scoring, and the First Federated Recall Benchmark

Key Points

This research introduces a federated cognitive memory architecture aimed at improving memory retrieval among agents.
Developed a federated cognitive memory system combining Complementary Learning Systems with tiered access layers (L0-L3).
Implemented semiotic density scoring to prioritize high-value memories during retrieval.
Conducted experiments with 4 SYMBIONT-IMI synergies to evaluate memory retrieval effectiveness.
Memory retrieval quality was significantly improved by using organism-level signals and memory tiering (p<0.05).
Achieved economical wake-up costs of approximately 200 tokens, compared to the baseline of 2K tokens.
The L0-L3 hierarchical structure facilitated predictable context budgeting during memory retrieval.

Abstract

We present a federated cognitive memory architecture that combines Complementary Learning Systems (CLS) with a tiered access VIEW layer (L0-L3) and semiotic density scoring for multi-agent systems. The system enables agents to share memories through a governed bus (FCM) with membrane filtering, while maintaining economical wake-up costs (~200 tokens vs ~2K baseline). We introduce FederatedRecall, the first benchmark for measuring cross-agent memory retrieval quality. Experiments with 4 SYMBIONT-IMI synergies demonstrate that organism-level signals (channel weights, artifact approval, priority shifts) can inform memory tiering without replacing the underlying biological memory model. The L0-L3 hierarchy provides predictable context budgeting while the semiotic density scoring layer ensures high-value memories surface first during retrieval under token pressure.

Read Full Paperexternally

Ask AI

Helpful

Bookmark

View Full Paper