Cover Image

Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jahn, Felix, Muskalla, Yannic, Dargasz, Lisa, Schramowski, Patrick, Baum, Kevin
Format:	Preprint
Published:	2026
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

Acting for the Right Reasons: Creating Reason-Sensitive Artificial Moral Agents
by: Baum, Kevin, et al.
Published: (2024)

Integrating Reason-Based Moral Decision-Making in the Reinforcement Learning Architecture
by: Dargasz, Lisa
Published: (2025)

Legal Alignment for Safe and Ethical AI
by: Kolt, Noam, et al.
Published: (2026)

Modularizing Educational LLM-Agency for Fostering Responsible Learning Assistance
by: Gabelmann, Julius, et al.
Published: (2026)

Justifications for Democratizing AI Alignment and Their Prospects
by: Steingrüber, André, et al.
Published: (2025)

Disentangling AI Alignment: A Structured Taxonomy Beyond Safety and Ethics
by: Baum, Kevin
Published: (2025)

Pluralism in AI Governance: Toward Sociotechnical Alignment and Normative Coherence
by: Nkongolo, Mike Wa
Published: (2026)

AI Alignment vs. AI Ethical Treatment: 10 Challenges
by: Bradley, Adam, et al.
Published: (2025)

Constitutive vs. Corrective: A Causal Taxonomy of Human Runtime Involvement in AI Systems
by: Baum, Kevin, et al.
Published: (2026)

Beyond Monolithic Models: Symbolic Seams for Composable Neuro-Symbolic Architectures
by: Schuler, Nicolas, et al.
Published: (2026)

The Value of Gen-AI Conversations: A bottom-up Framework for AI Value Alignment
by: Motnikar, Lenart, et al.
Published: (2025)

Beyond Personhood: Agency, Accountability, and the Limits of Anthropomorphic Ethical Analysis
by: Dai, Jessica
Published: (2024)

Beyond Overcorrection: Evaluating Diversity in T2I Models with DivBench
by: Friedrich, Felix, et al.
Published: (2025)

Privacy Ethics Alignment in AI: A Stakeholder-Centric Framework for Ethical AI
by: Barthwal, Ankur, et al.
Published: (2025)

Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment
by: Corrêa, Nicholas Kluge
Published: (2024)

Alignment, Agency and Autonomy in Frontier AI: A Systems Engineering Perspective
by: Tallam, Krti
Published: (2025)

Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Language Models
by: Quirke, Philip, et al.
Published: (2025)

From the AI Act to a European AI Agency: Completing the Union's Regulatory Architecture
by: Pavlidis, Georgios
Published: (2026)

LEGOS-SLEEC: Tool for Formalizing and Analyzing Normative Requirements
by: Kolyakov, Kevin, et al.
Published: (2025)

The Illusory Normativity of Rights-Based AI Regulation
by: Mei, Yiyang, et al.
Published: (2025)

"Ethical Neutrinos: A Neuro-Symbolic Framework for Minimalist Ethical Alignment in Artificial Intelligence".
by: MANJARREZ, ANTONIO
Published: (2025)

A Neuro-Symbolic Framework for Accountability in Public-Sector AI
by: Sunny, Allen Daniel, et al.
Published: (2025)

Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You
by: Friedrich, Felix, et al.
Published: (2024)

Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis
by: Struppek, Lukas, et al.
Published: (2022)

On the Complexities of Testing for Compliance with Human Oversight Requirements in AI Regulation
by: Langer, Markus, et al.
Published: (2025)

Can AI Rely on the Systematicity of Truth? The Challenge of Modelling Normative Domains
by: Queloz, Matthieu
Published: (2025)

Breaking Down the Scoring: Interrater Reliability and National Bias in Olympic Breaking
by: Braeunig, Patrick Alexander
Published: (2025)

Ethical Implications of Training Deceptive AI
by: Starace, Jason, et al.
Published: (2026)

ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming
by: Tedeschi, Simone, et al.
Published: (2024)

Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
by: Ostermann, Simon, et al.
Published: (2024)

EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI
by: Kasu, Sai Kartheek Reddy
Published: (2025)

Ethical Leadership in the Age of AI Challenges, Opportunities and Framework for Ethical Leadership
by: Kandasamy, Udaya Chandrika
Published: (2024)

Catalog of General Ethical Requirements for AI Certification
by: Corrêa, Nicholas Kluge, et al.
Published: (2024)

Towards an Atomic Agency for Quantum-AI
by: Kop, Mauritz
Published: (2025)

Competing Visions of Ethical AI: A Case Study of OpenAI
by: Wilfley, Melissa, et al.
Published: (2026)

Normative Moral Pluralism for AI: A Framework for Deliberation in Complex Moral Contexts
by: Yaacov, David-Doron
Published: (2025)

Augmentation Technologies and AI - An Ethical Design Futures Framework
by: Duin, Ann Hill, et al.
Published: (2025)

A Moral Agency Framework for Legitimate Integration of AI in Bureaucracies
by: Schmitz, Chris, et al.
Published: (2025)

Who Decides in AI-Mediated Learning? The Agency Allocation Framework
by: Borchers, Conrad, et al.
Published: (2026)

CogniAlign: Survivability-Grounded Multi-Agent Moral Reasoning for Safe and Transparent AI
by: Ali, Hasin Jawad, et al.
Published: (2025)