Safety Must Precede the Deployment of Open-Ended AI

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sheth, Ivaxi, Wehner, Jan, Abdelnabi, Sahar, Binkyte, Ruta, Fritz, Mario
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913178325090304
author Sheth, Ivaxi
Wehner, Jan
Abdelnabi, Sahar
Binkyte, Ruta
Fritz, Mario
author_facet Sheth, Ivaxi
Wehner, Jan
Abdelnabi, Sahar
Binkyte, Ruta
Fritz, Mario
contents AI advancements have been significantly driven by a combination of foundation models and curiosity-driven learning aimed at increasing capability and adaptability. Within this landscape, open-endedness, where AI agents autonomously and indefinitely generate novel behaviors, representations, or solutions, has gained increasing interest. This has become relevant in the context of self-evolving agents and long-horizon discovery. This position paper argues that the defining properties of open-ended AI systems introduce a distinct and underexplored class of safety challenges, including loss of predictability, emergent misalignment, and difficulties in maintaining effective control as systems evolve beyond their initial design assumptions, that must be addressed preemptively. These challenges differ qualitatively from those associated with task-bounded or static models and are unlikely to be addressed by existing safety frameworks alone, which is why these risks must be examined proactively, before large-scale deployment. The paper proposes a taxonomy for key challenges, discusses research opportunities, and calls for coordinated action to support the safe and responsible development of open-ended AI.
format Preprint
id arxiv_https___arxiv_org_abs_2502_04512
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Safety Must Precede the Deployment of Open-Ended AI
Sheth, Ivaxi
Wehner, Jan
Abdelnabi, Sahar
Binkyte, Ruta
Fritz, Mario
Artificial Intelligence
AI advancements have been significantly driven by a combination of foundation models and curiosity-driven learning aimed at increasing capability and adaptability. Within this landscape, open-endedness, where AI agents autonomously and indefinitely generate novel behaviors, representations, or solutions, has gained increasing interest. This has become relevant in the context of self-evolving agents and long-horizon discovery. This position paper argues that the defining properties of open-ended AI systems introduce a distinct and underexplored class of safety challenges, including loss of predictability, emergent misalignment, and difficulties in maintaining effective control as systems evolve beyond their initial design assumptions, that must be addressed preemptively. These challenges differ qualitatively from those associated with task-bounded or static models and are unlikely to be addressed by existing safety frameworks alone, which is why these risks must be examined proactively, before large-scale deployment. The paper proposes a taxonomy for key challenges, discusses research opportunities, and calls for coordinated action to support the safe and responsible development of open-ended AI.
title Safety Must Precede the Deployment of Open-Ended AI
topic Artificial Intelligence
url https://arxiv.org/abs/2502.04512