Forgetful but Faithful: A Cognitive Memory Architecture and Benchmark for Privacy-Aware Generative Agents

TL;DR

This paper introduces MaRS, a new memory management framework with six forgetting policies for generative agents, and the FiFA benchmark to evaluate their performance, privacy, and efficiency in long-term scenarios.

Contribution

It proposes the Memory-Aware Retention Schema (MaRS) and six theoretically-grounded forgetting policies, along with the FiFA benchmark for comprehensive evaluation.

Findings

Hybrid forgetting policy achieves a composite score of 0.911.

Memory management improves agent coherence and privacy.

Framework is effective across multiple memory budgets and configurations.

Abstract

As generative agents become increasingly sophisticated and deployed in long-term interactive scenarios, their memory management capabilities emerge as a critical bottleneck for both performance and privacy. Current approaches either maintain unlimited memory stores, leading to computational intractability and privacy concerns, or employ simplistic forgetting mechanisms that compromise agent coherence and functionality. This paper introduces the Memory-Aware Retention Schema (MaRS), a novel framework for human-centered memory management in generative agents, coupled with six theoretically-grounded forgetting policies that balance performance, privacy, and computational efficiency. We present the Forgetful but Faithful Agent (FiFA) benchmark, a comprehensive evaluation framework that assesses agent performance across narrative coherence, goal completion, social recall accuracy, privacy preservation, and cost efficiency. Through extensive experimentation involving 300 evaluation runs across multiple memory budgets and agent configurations, we demonstrate that our hybrid forgetting policy achieves superior performance (composite score: 0.911) while maintaining computational tractability and privacy guarantees. Our work establishes new benchmarks for memory-budgeted agent evaluation and provides practical guidelines for deploying generative agents in resource-constrained, privacy-sensitive environments. The theoretical foundations, implementation framework, and empirical results contribute to the emerging field of human-centered AI by addressing fundamental challenges in agent memory management that directly impact user trust, system scalability, and regulatory compliance.