FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory

2026-04-22

AI Summary

This study addresses the absence of biologically inspired, efficient, secure, and high-quality selective forgetting mechanisms in large language model (LLM) agents operating under resource-constrained conditions. The authors propose a novel cognitive-inspired framework that integrates hippocampal indexing/consolidation theory with the Ebbinghaus forgetting curve, systematically establishing a selective forgetting architecture comprising four mechanisms: passive decay, active deletion, security-triggered erasure, and adaptive reinforcement. Implemented within an LLM agent framework coupled with a vector database, this approach enables dynamic memory management. Experimental results demonstrate that the proposed framework improves memory retrieval efficiency by 8.49%, enhances content signal-to-noise ratio by 29.2%, and completely eliminates security risks arising from sensitive or malicious information.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting--inspired by human cognitive processes (hippocampal indexing/consolidation theory and Ebbinghaus forgetting curve)--remains underexplored. We argue that in resource-constrained environments, a well-designed forgetting mechanism is as crucial as remembering, delivering benefits across three dimensions: (1) efficiency via intelligent memory pruning, (2) quality by dynamically updating outdated preferences and context, and (3) security through active forgetting of malicious inputs, sensitive data, and privacy-compromising content. Our framework establishes a taxonomy of forgetting mechanisms: passive decay-based, active deletion-based, safety-triggered, and adaptive reinforcement-based. Building on advances in LLM agent architectures and vector databases, we present detailed specifications, implementation strategies, and empirical validation from controlled experiments. Results show significant improvements: access efficiency (+8.49%), content quality (+29.2% signal-to-noise ratio), and security performance (100% elimination of security risks). Our work bridges cognitive neuroscience and AI systems, offering practical solutions for real-world deployment while addressing ethical and regulatory compliance. The paper concludes with challenges and future directions, establishing selective forgetting as a fundamental capability for next-generation LLM agents operating in real-world, resource-constrained scenarios. Our contributions align with AI-native memory systems and responsible AI development.

Problem

• selective forgetting
• memory management
• LLM agents
• resource-constrained environments
• security

Innovation

• selective forgetting
• biologically-inspired AI
• LLM agent memory
• memory management
• responsible AI