{"ID":2864242,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23757","arxiv_id":"2509.23757","title":"Transparent Visual Reasoning via Object-Centric Agent Collaboration","abstract":"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.","short_abstract":"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 t...","url_abs":"https://arxiv.org/abs/2509.23757","url_pdf":"https://arxiv.org/pdf/2509.23757v1","authors":"[\"Benjamin Teoh\",\"Ben Glocker\",\"Francesca Toni\",\"Avinash Kori\"]","published":"2025-09-28T09:06:52Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CV\"]","methods":"[]","has_code":false}