The paper "Value-Preserving Architectures for Agentic AI Systems" discusses how architectural choices in large language model-based multi‑agent systems (MAS) can promote human‑centered values such as privacy, fairness, and safety. It introduces three value‑preserving architectural patterns: a privacy‑aware federated topology, a distributed architecture that encourages pluralism and diversity, and a guard‑agent design to detect and mitigate unfairness. Representative use cases illustrate how these patterns can be applied in real‑world scenarios, aiming to provide guidelines for building trustworthy MAS.
By Alessandro Pesare, Tommaso Dolci, Katja Hose, Emanuel Sallinger
arXiv:2608. 10327v1 Announce Type: new Abstract: Can AI systems be aligned to human values?
By Andrew Smart, Shazeda Ahmed, Jackie Kay, Jimmy Tobin, Kris Shrishak, Abeba Birhane
arXiv:2608. 03910v1 Announce Type: new Abstract: As AI systems are deployed across increasingly diverse social contexts, alignment can no longer be framed as the optimization of a single, unified set of values.
By Matt Ratto, Abhishek Moturu, Daniel Silver
arXiv:2601. 21700v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly support culturally sensitive decision making, yet often exhibit misalignment due to skewed pretraining data and the absence of structured value representations.
By Wonduk Seo, Wonseok Choi, Junseo Koh, Juhyeon Lee, Hyunjin An, Minhyeong Yu, Jian Park, Qingshan Zhou, Seunghyun Lee, Yi Bu
arXiv:2607. 16903v1 Announce Type: cross Abstract: Value-aware AI systems require explicit computational representations of human values (groundings) and their aggregation into value systems in order to align their decisions with ours.
By Andr\'es Holgado-S\'anchez, Holger Billhardt, Sascha Ossowski
ExpertIVS is a framework that uses 14 sociological expert agents to interpret World Values Survey responses, reconstructing individual value systems in a coherent, internally consistent manner rather than simply concatenating survey answers. It introduces a multi‑agent debate mechanism to assess LLM alignment with these value profiles during dynamic interactions. Experiments on 480 individuals from 12 countries show a 90.78% value restoration fidelity and a 5.3% improvement in value generalization over baseline methods, while also demonstrating strong personality discriminability and behavioral consistency.
By Zhen Wang, Yuqi Ren, Yuehan Cui, Hongxiang Wang, Jianxiang Peng, Zhaoxia Zhang, Bingkun Zhu, Tongxuan Zhang, Dezhi Tong, Deyi Xiong