Metraipolis › archive › dc_8bd8aabe7b6c
Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment — arXiv:2609.05036
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.05036
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T22:21:07.367Z
- SHA-256 of the archived text
3dc50e15db96fdf5b65bfba4209ac99124bf86e79b3c1e98b90eb15630783d98- Stable URL of this page
https://metraipolis.com/documento/dc_8bd8aabe7b6c
How to cite
Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment — arXiv:2609.05036 — arXiv (en), https://arxiv.org/abs/2609.05036 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8bd8aabe7b6c (Metraipolis archive dc_8bd8aabe7b6c, sha256 3dc50e15db96fdf5b65bfba4209ac99124bf86e79b3c1e98b90eb15630783d98)
BibTeX
@misc{dc8bd8aabe7b6c,
title = {Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment — arXiv:2609.05036},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.05036},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8bd8aabe7b6c; sha256 3dc50e15db96fdf5b65bfba4209ac99124bf86e79b3c1e98b90eb15630783d98},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05036. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI alignment requires AI systems to adhere to human norms, values, or intentions. Under value pluralism there is no correct target, but a shared prerequisite is that the system's behavior expresses a coherent policy: a mapping from situations to verdicts that is invariant while a situation's morally relevant features are preserved, and sensitive when they change. We introduce four structural conditions for such coherent policies: verdict stability, monotonicity, decisiveness, and Pareto viability. Together they measure a form of moral competence that is evaluable from behavior alone, without reference to a moral standard or expert baseline, forming a structural floor for alignment rather than a normative target. We demonstrate the methodology on three simulated deployments featuring LLM-based agents facing moral dilemmas. Evaluating nine frontier models under a factorial design of five paraphrases, five escalation levels, and three dominance conditions, we show no model expresses a coherent policy across the three deployments: surface-form perturbation alone produces verdict-rate shifts of up to $99$ percentage points at a single escalation level, and a model's success on one scenario does not predict its competence on another. This suggests LLM-based agents are not currently the kind of object to which alignment can meaningfully apply. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Computers and Society (cs.CY). Pagina del lavoro: https://arxiv.org/abs/2609.05036 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T22:18:11.425Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).