Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	DeChant, Chad
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computers and Society
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Episodic Memory Verbalization using Hierarchical Representations of Life-Long Robot Experience
by: Bärmann, Leonard, et al.
Published: (2024)

Giving AI a voice: how does AI think it should be treated?
by: Fay, Maria, et al.
Published: (2025)

The 2025 OpenAI Preparedness Framework does not guarantee any AI risk mitigation practices: a proof-of-concept for affordance analyses of AI safety policies
by: Coggins, Sam, et al.
Published: (2025)

How should AI decisions be explained? Requirements for Explanations from the Perspective of European Law
by: Fresz, Benjamin, et al.
Published: (2024)

What hackers talk about when they talk about AI: Early-stage diffusion of a cybercrime innovation
by: Dupont, Benoît, et al.
Published: (2026)

Affirmative safety: An approach to risk management for high-risk AI
by: Wasil, Akash R., et al.
Published: (2024)

The Convergent Ethics of AI? Analyzing Moral Foundation Priorities in Large Language Models with a Multi-Framework Approach
by: Coleman, Chad, et al.
Published: (2025)

Risks of AI-driven product development and strategies for their mitigation
by: Göpfert, Jan, et al.
Published: (2025)

Human-Provenance Verification should be Treated as Labor Infrastructure in AI-Saturated Markets
by: McGurk, Erin, et al.
Published: (2026)

AI-Assisted Systematization for Evaluating GenAI Systems
by: Agarwal, Dhruv, et al.
Published: (2026)

Contemporary AI foundation models increase biological weapons risk
by: Brent, Roger, et al.
Published: (2025)

US-China perspectives on extreme AI risks and global governance
by: Wasil, Akash, et al.
Published: (2024)

Analyzing the Ethical Logic of Six Large Language Models
by: Neuman, W. Russell, et al.
Published: (2025)

What AI evaluations for preventing catastrophic risks can and cannot do
by: Barnett, Peter, et al.
Published: (2024)

The Third Ambition: Artificial Intelligence and the Science of Human Behavior
by: Neuman, W. Russell, et al.
Published: (2026)

Human services organizations and the responsible integration of AI: Considering ethics and contextualizing risk(s)
by: Perron, Brian E., et al.
Published: (2025)

Enhancing transparency in AI-powered customer engagement
by: DeZao, Tara
Published: (2024)

Which Information should the UK and US AISI share with an International Network of AISIs? Opportunities, Risks, and a Tentative Proposal
by: Thurnherr, Lara
Published: (2025)

Assessing the State of AI Policy
by: DeFranco, Joanna F., et al.
Published: (2024)

Quantitative study about the estimated impact of the AI Act
by: Hauer, Marc P., et al.
Published: (2023)

AI Companions Reduce Loneliness
by: De Freitas, Julian, et al.
Published: (2024)

Will artificial agents pursue power by default?
by: Tarsney, Christian
Published: (2025)

Mapping Human Anti-collusion Mechanisms to Multi-agent AI Systems
by: Idowu, Jamiu, et al.
Published: (2026)

A Marketplace for AI-Generated Adult Content and Deepfakes
by: Ghosh, Shalmoli, et al.
Published: (2026)

Governing frontier general-purpose AI in the public sector: adaptive risk management and policy capacity under uncertainty through 2030
by: Xavier, Fabio Correa
Published: (2026)

Understanding the Process of Human-AI Value Alignment
by: McKinlay, Jack, et al.
Published: (2025)

Position: The Most Expensive Part of an LLM should be its Training Data
by: Kandpal, Nikhil, et al.
Published: (2025)

The potential functions of an international institution for AI safety. Insights from adjacent policy areas and recent trends
by: De Castris, A. Leone, et al.
Published: (2024)

Particip-AI: A Democratic Surveying Framework for Anticipating Future AI Use Cases, Harms and Benefits
by: Mun, Jimin, et al.
Published: (2024)

The potential role of AI agents in transforming nuclear medicine research and cancer management in India
by: Vashistha, Rajat, et al.
Published: (2025)

Conformity and Social Impact on AI Agents
by: Bellina, Alessandro, et al.
Published: (2026)

Towards medical AI misalignment: a preliminary study
by: Puccio, Barbara, et al.
Published: (2025)

Evaluating undergraduate mathematics examinations in the era of generative AI: a curriculum-level case study
by: Walker, Benjamin J., et al.
Published: (2025)

Teaching Introduction to Programming in the times of AI: A case study of a course re-design
by: Avouris, Nikolaos, et al.
Published: (2025)

Governing dual-use technologies: Case studies of international security agreements and lessons for AI governance
by: Wasil, Akash R., et al.
Published: (2024)

Managing extreme AI risks amid rapid progress
by: Bengio, Yoshua, et al.
Published: (2023)

Security, privacy, and agentic AI in a regulatory view: From definitions and distinctions to provisions and reflections
by: Zhang, Shiliang, et al.
Published: (2026)

Artificially intelligent agents in the social and behavioral sciences: A history and outlook
by: Holme, Petter, et al.
Published: (2025)

A Knowledge-Component-Based Methodology for Evaluating AI Assistants
by: Qi, Laryn, et al.
Published: (2024)

From job titles to jawlines: Using context voids to study generative AI systems
by: Memon, Shahan Ali, et al.
Published: (2025)