Value-Aware Multiagent Systems

Nardine Osman
12/14/2025
cs.AIcs.MA

No confident code implementation found for this paper.

Abstract

This paper introduces the concept of value awareness in AI, which goes beyond the traditional value-alignment problem. Our definition of value awareness presents us with a concise and simplified roadmap for engineering value-aware AI. The roadmap is structured around three core pillars: (1) learning and representing human values using formal semantics, (2) ensuring the value alignment of both individual agents and multiagent systems, and (3) providing value-based explainability on behaviour. The paper presents a selection of our ongoing work on some of these topics, along with applications to real-life domains.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Human Values in Multiagent Systems

83% match2023

Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values

82% match2023

Rethinking How AI Embeds and Adapts to Human Values: Challenges and Opportunities

82% match2025

The Linguistic Blind Spot of Value-Aligned Agency, Natural and Artificial

80% match2022

A computational framework for human values

80% match2023

Modelling Human Values for AI Reasoning

80% match2024

Cite this paper

@article{osman2025valueaware,
  title  = {Value-Aware Multiagent Systems},
  author = {Nardine Osman},
  year   = {2025},
  eprint = {2512.12652},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2512.12652v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2512.12652.svg)](https://codeofpaper.com/paper/2512.12652)

Discussion