Cognifold: Always-On Proactive Memory via Cognitive Folding

TL;DR

Cognifold is an innovative, brain-inspired memory system for autonomous agents that continuously organizes experiences into cognitive structures, enabling proactive behavior and higher-level cognition.

Contribution

It extends CLS theory to three layers, introducing a prefrontal intent layer, and demonstrates proactive, self-organizing memory structures in autonomous agents.

Findings

Cognifold produces memory structures aligning with cognitive expectations.

It performs robustly across seven benchmarks in five cognitive domains.

Cognifold effectively merges, decays, and relinks memory structures based on semantic relevance.

Abstract

Existing agent memory remains predominantly reactive and retrieval-based, lacking the capacity to autonomously organize experience into persistent cognitive structure. Toward genuinely autonomous agents, we introduce Cognifold, a brain-inspired "always-on" agent memory designed for the next generation of proactive assistants. CogniFold continuously folds fragmented event streams into self-emerging cognitive structures, bootstrapping progressively higher-level cognition from incoming events and accumulated knowledge. We ground this by extending Complementary Learning Systems (CLS) theory from two layers (hippocampus, neocortex) to three, adding a prefrontal intent layer. Emulating the prefrontal cortex as the locus of intentional control and decision-making, CogniFold achieves this through graph-topology self-organization: cognitive structures proactively assemble under the stream, merge when semantically similar, decay when stale, relink through associative recall, and surface intents when concept-cluster density crosses a threshold. We evaluate structural formation using CogEval-Bench, demonstrating that CogniFold uniquely produces memory structures that match cognitive expectations and concept emergence. Furthermore, across 7 broad-coverage benchmarks spanning five cognitive domains, we validate that CogniFold simultaneously performs robustly on conventional memory benchmarks.