{"ID":2866757,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.20490","arxiv_id":"2509.20490","title":"RadAgents: Multimodal Agentic Reasoning for Chest X-ray Interpretation with Radiologist-like Workflows","abstract":"Agentic systems offer a potential path to solve complex clinical tasks through collaboration among specialized agents, augmented by tool use and external knowledge bases. Nevertheless, for chest X-ray (CXR) interpretation, prevailing methods remain limited: (i) reasoning is frequently neither clinically interpretable nor aligned with guidelines, reflecting mere aggregation of tool outputs; (ii) multimodal evidence is insufficiently fused, yielding text-only rationales that are not visually grounded; and (iii) systems rarely detect or resolve cross-tool inconsistencies and provide no principled verification mechanisms. To bridge the above gaps, we present RadAgents, a multi-agent framework that couples clinical priors with task-aware multimodal reasoning and encodes a radiologist-style workflow into a modular, auditable pipeline. In addition, we integrate grounding and multimodal retrieval-augmentation to verify and resolve context conflicts, resulting in outputs that are more reliable, transparent, and consistent with clinical practice.","short_abstract":"Agentic systems offer a potential path to solve complex clinical tasks through collaboration among specialized agents, augmented by tool use and external knowledge bases. Nevertheless, for chest X-ray (CXR) interpretation, prevailing methods remain limited: (i) reasoning is frequently neither clinically interpretable n...","url_abs":"https://arxiv.org/abs/2509.20490","url_pdf":"https://arxiv.org/pdf/2509.20490v4","authors":"[\"Kai Zhang\",\"Corey D Barrett\",\"Jangwon Kim\",\"Lichao Sun\",\"Tara Taghavi\",\"Krishnaram Kenthapadi\"]","published":"2025-09-24T19:08:01Z","proceeding":"cs.MA","tasks":"[\"cs.MA\",\"cs.CL\",\"cs.CV\"]","methods":"[]","has_code":false}