{"ID":2865135,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.22014","arxiv_id":"2509.22014","title":"Lightweight Structured Multimodal Reasoning for Clinical Scene Understanding in Robotics","abstract":"Healthcare robotics requires robust multimodal perception and reasoning to ensure safety in dynamic clinical environments. Current Vision-Language Models (VLMs) demonstrate strong general-purpose capabilities but remain limited in temporal reasoning, uncertainty estimation, and structured outputs needed for robotic planning. We present a lightweight agentic multimodal framework for video-based scene understanding. Combining the Qwen2.5-VL-3B-Instruct model with a SmolAgent-based orchestration layer, it supports chain-of-thought reasoning, speech-vision fusion, and dynamic tool invocation. The framework generates structured scene graphs and leverages a hybrid retrieval module for interpretable and adaptive reasoning. Evaluations on the Video-MME benchmark and a custom clinical dataset show competitive accuracy and improved robustness compared to state-of-the-art VLMs, demonstrating its potential for applications in robot-assisted surgery, patient monitoring, and decision support.","short_abstract":"Healthcare robotics requires robust multimodal perception and reasoning to ensure safety in dynamic clinical environments. Current Vision-Language Models (VLMs) demonstrate strong general-purpose capabilities but remain limited in temporal reasoning, uncertainty estimation, and structured outputs needed for robotic pla...","url_abs":"https://arxiv.org/abs/2509.22014","url_pdf":"https://arxiv.org/pdf/2509.22014v1","authors":"[\"Saurav Jha\",\"Stefan K. Ehrlich\"]","published":"2025-09-26T07:49:49Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.HC\",\"cs.RO\"]","methods":"[\"Language Model\"]","has_code":false}