Episodic memory in AI agents poses risks that should be studied and mitigated

TL;DR

This paper discusses the potential benefits and risks of integrating episodic memory into AI agents, emphasizing the need for guidelines to ensure safety and trustworthiness.

Contribution

It highlights the importance of episodic memory in AI, outlines associated risks, and proposes principles for safe development of memory capabilities.

Findings

Episodic memory can improve AI capabilities in recall and planning.

Memory integration poses new safety and trust risks.

Guidelines are proposed to mitigate risks and enhance safety.

Abstract

Most current AI models have little ability to store and later retrieve a record or representation of what they do. In human cognition, episodic memories play an important role in both recall of the past as well as planning for the future. The ability to form and use episodic memories would similarly enable a broad range of improved capabilities in an AI agent that interacts with and takes actions in the world. Researchers have begun directing more attention to developing memory abilities in AI models. It is therefore likely that models with such capability will be become widespread in the near future. This could in some ways contribute to making such AI agents safer by enabling users to better monitor, understand, and control their actions. However, as a new capability with wide applications, we argue that it will also introduce significant new risks that researchers should begin to study and address. We outline these risks and benefits and propose four principles to guide the development of episodic memory capabilities so that these will enhance, rather than undermine, the effort to keep AI safe and trustworthy.