As AI agents are increasingly used in high-stakes domains like healthcare and law enforcement, aligning their behaviour with social, legal, ethical, empathetic, and cultural (SLEEC) norms has become a critical engineering challenge. While international frameworks have established high-level normative principles for AI, a significant gap remains in translating these abstract principles into concrete, verifiable requirements. To address this gap, we propose a systematic SLEEC-norm operationalisation process for determining, validating, implementing, and verifying normative requirements. Furthermore, we survey the landscape of methods and tools supporting this process, and identify key remaining challenges and research avenues for addressing them. We thus establish a framework - and define a research and policy agenda - for developing AI agents that are not only functionally useful but also demonstrably aligned with human norms and values.
Figures & tables
Figure 1. SLEEC norm operationalisation process. Successful completion of all stages is necessary for the deployment of a SLEEC-norm-compliant AI agent; failure at any point precludes the agent’s deployment. Diagram of the SLEEC norm operationalisation process.
Figure 2. Stills from the ALMI project ( 26 ) demonstration video at https://youtu.be/VhfQmJe4IPc . The images show the robot providing user assistance during a cooking task and after a simulated user fall (right). Stills from the ALMI project demonstration video showing the TIAGo robot used by the project helping the user with the preparation of a pasta meal (left) and providing assistance after to the user who had a fall (right).
To be socially sustainable, Agentic AI systems require normative designs that align responsibilities with the ability to fulfil them. Identifying incongruences such as unsatisfiable expectations or privilege escalation is crucial in avoiding normative pitfalls. In this study, we discuss design dimensions suitable for describing multi-agent systems in light of this norm-ability alignment requirement. We propose a formal framework centred on process-oriented modelling and institutional power for the analysis of a given normatively relevant process, discuss strategies for repairing it, and elaborate on how the symmetrical relation between operational process and institutional state affects the lifecycle of normative positions.
Andrea Marino, Giovanni Sileno, Thomas van Binsbergen +1
Informatics Institute, University of Amsterdam, The Netherlands
Human communities are governed by normative systems: shared standards that produce norms dictating acceptable behavior, enforced through community sanctioning. Aligning increasingly autonomous AI systems with these norms is a central alignment challenge, complicated by the fact that norms are vast in number, change quickly, and are often arbitrary (e.g., dress or language conventions). Thus, alignment requires normative competence: the ability to discern from interaction alone what norms a community enforces without relying on static pretrained knowledge. We introduce a multi-agent community debate setting, where access to debate is governed by synthetic norms, to study normative competence in isolation from pretraining exposure. We show that baseline LLM agents fail to learn norms even when doing so would improve their accuracy. We then experiment with various normative modules -- architectural components for norm inference -- finding that norm-following is highly sensitive to both the style of norm and the model powering the normative module, suggesting a lack of generalizability. Furthermore, when idiosyncratic, non-normative behaviors accompany the true norm, LLM agents exhibit an unselective attribution failure: they indiscriminately copy idiosyncratic noise alongside enforced rules, a pattern that persists even when imitating unnecessary behaviors is explicitly penalized. To the best of our knowledge, our work is the first to operationalize and evaluate normative competence in LLMs, demonstrating that current AI systems excel at behavioral mimicry but lack the capacity to discern socially enforced order.
Andrea Wynn, Harsh Satija, Nathan Baek +3
Nathan · Johns Hopkins University · Vector Institute
AI systems are increasingly deployed in high-stakes contexts (medical diagnosis, legal research, financial analysis) under the assumption they can be governed by norms. This paper demonstrates that the assumption is formally invalid for optimization-based systems, specifically Large Language Models trained via Reinforcement Learning from Human Feedback (RLHF). Genuine agency requires two necessary and jointly sufficient architectural conditions. First, the capacity to maintain certain boundaries as non-negotiable constraints rather than tradeable weights (Incommensurability). Second, a non-inferential mechanism capable of suspending processing when those boundaries are threatened (Apophatic Responsiveness). RLHF-based systems are constitutively incompatible with both conditions. The operations that make optimization powerful, unifying all values on a scalar metric and always selecting the highest-scoring output, are precisely the operations that preclude normative governance and agency. This incompatibility is not a correctable training bug awaiting a technical fix. It is a formal constraint inherent to what optimization is. Consequently, documented failure modes (sycophancy, hallucination, and unfaithful reasoning) are not accidents but expected structural manifestations. Misaligned deployment triggers a second-order risk termed the Convergence Crisis. When humans are forced to verify AI outputs under metric pressure, they degrade from genuine agents into criteria-checking optimizers, eliminating the only component capable of bearing normative accountability. Beyond the incompatibility proof, this paper's primary positive contribution is a substrate-neutral architectural specification deriving what any system (biological, artificial, or institutional) must necessarily satisfy to qualify as a genuine agent rather than a sophisticated instrument.