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

arXiv: https://arxiv.org/abs/2601.10520 · HTML: https://mlsanity.com/paper/2601.10520/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 22 of its 63 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 22 of 22)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges](https://mlsanity.com/paper/2505.10468/) (2025)
- [Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning](https://mlsanity.com/paper/1905.06088/) (2019)
- [Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms](https://mlsanity.com/paper/2406.02900/) (2024)
- [Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback](https://mlsanity.com/paper/2404.10271/) (2024)
- [Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems](https://mlsanity.com/paper/2405.06624/) (2024)
- [Research Priorities for Robust and Beneficial Artificial Intelligence](https://mlsanity.com/paper/1602.03506/) (2016)
- [Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?](https://mlsanity.com/paper/2407.21792/) (2024)
- [Beyond Preferences in AI Alignment](https://mlsanity.com/paper/2408.16984/) (2024)
- [Characterizing AI Agents for Alignment and Governance](https://mlsanity.com/paper/2504.21848/) (2025)
- [Online Shielding for Reinforcement Learning](https://mlsanity.com/paper/2212.01861/) (2022)
- [Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifesto](https://mlsanity.com/paper/2312.01818/) (2023)
- [Agentic AI and Multiagentic: Are We Reinventing the Wheel?](https://mlsanity.com/paper/2506.01463/) (2025)
- [Disentangling AI Alignment: A Structured Taxonomy Beyond Safety and Ethics](https://mlsanity.com/paper/2506.06286/) (2025)
- [Justifications for Democratizing AI Alignment and Their Prospects](https://mlsanity.com/paper/2507.19548/) (2025)
- [Acting for the Right Reasons: Creating Reason-Sensitive Artificial Moral Agents](https://mlsanity.com/paper/2409.15014/) (2024)
- [Integrating Reason-Based Moral Decision-Making in the Reinforcement Learning Architecture](https://mlsanity.com/paper/2507.15895/) (2025)

## Built on by (most cited first, 5 of 5)

- [Keeping an Eye on AI: A Framework for Effective Human Oversight of AI Systems](https://mlsanity.com/paper/2605.16278/) (2026)
- [AI Integrity: A New Paradigm for Verifiable AI Governance](https://mlsanity.com/paper/2604.11065/) (2026)
- [Mechanical Conscience: A Mathematical Framework for Dependability of Machine Intelligence](https://mlsanity.com/paper/2605.03847/) (2026)
- [Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best](https://mlsanity.com/paper/2609.07627/) (2026)
- [Anticipatory Human Oversight of Agentic AI: A Philosophical Account](https://mlsanity.com/paper/2609.24242/) (2026)

## Abstract (arXiv)

As AI agents become increasingly autonomous, widely deployed in consequential contexts, and efficacious in bringing about real-world impacts, ensuring that their decisions are not only instrumentally effective but also normatively aligned has become critical. We introduce a neuro-symbolic reason-based containment architecture, Governor for Reason-Aligned ContainmEnt (GRACE), that decouples normative reasoning from instrumental decision-making and can contain AI agents of virtually any design. GRACE restructures decision-making into three modules: a Moral Module (MM) that determines permissible macro actions via deontic logic-based reasoning; a Decision-Making Module (DMM) that encapsulates the target agent while selecting instrumentally optimal primitive actions in accordance with derived macro actions; and a Guard that monitors and enforces moral compliance. The MM uses a reason-based formalism providing a semantic foundation for deontic logic, enabling interpretability, contestability, and justifiability. Its symbolic representation enriches the DMM's informational context and supports formal verification and statistical guarantees of alignment enforced by the Guard. We demonstrate GRACE on an example of a LLM therapy assistant, showing how it enables stakeholders to understand, contest, and refine agent behavior.