A central challenge in explainable AI, particularly in the visual domain, is producing explanations grounded in human-understandable concepts. To tackle this, we introduce OCEAN (Object-Centric Explananda via Agent Negotiation), a novel, inherently interpretable framework built on object-centric representations and a transparent multi-agent reasoning process. The game-theoretic reasoning process drives agents to agree on coherent and discriminative evidence, resulting in a faithful and interpretable decision-making process. We train OCEAN end-to-end and benchmark it against standard visual classifiers and popular posthoc explanation tools like GradCAM and LIME across two diagnostic multi-object datasets. Our results demonstrate competitive performance with respect to state-of-the-art black-box models with a faithful reasoning process, which was reflected by our user study, where participants consistently rated OCEAN's explanations as more intuitive and trustworthy.
@article{arxiv.2509.23757,
title = {Transparent Visual Reasoning via Object-Centric Agent Collaboration},
author = {Benjamin Teoh and Ben Glocker and Francesca Toni and Avinash Kori},
journal= {arXiv preprint arXiv:2509.23757},
year = {2025}
}