{"ID":5551851,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T07:28:02.592842364Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00544","arxiv_id":"2607.00544","title":"GEAR-Seg: A Grounded Explainable Agent for Reasoning Segmentation and Data Engine","abstract":"Reasoning segmentation requires localizing targets based on complex, implicit queries. Current end-to-end models typically entangle perception and deduction into an opaque black box, severely limiting interpretability and scalability. To address this, we propose GEAR-Seg (Grounded Explainable Agent for Reasoning Segmentation), an explicitly decoupled agent that shifts the paradigm by translating visual pixels into dense, attribute-rich text. By decoupling class-agnostic segmentation, semantic description, and Large Language Model (LLM) deduction, GEAR-Seg transforms implicit reasoning into an explicit, trackable logic chain. As a zero-shot inference framework, it achieves highly competitive performance across diverse reasoning and fine-grained referring segmentation benchmarks. Furthermore, GEAR-Seg inherently functions as a highly scalable data engine. Utilizing this engine, we construct GEAR-131K, a massive benchmark (over 38k images, 656k QA-mask pairs) introducing a multifaceted taxonomy tailored for complex real-world manipulation-oriented reasoning. Finally, distillation experiments demonstrate that lightweight models supervised exclusively by our automated pipeline closely match the upper-bound performance of costly human-annotated baselines.","short_abstract":"Reasoning segmentation requires localizing targets based on complex, implicit queries. Current end-to-end models typically entangle perception and deduction into an opaque black box, severely limiting interpretability and scalability. To address this, we propose GEAR-Seg (Grounded Explainable Agent for Reasoning Segmen...","url_abs":"https://arxiv.org/abs/2607.00544","url_pdf":"https://arxiv.org/pdf/2607.00544v1","authors":"[\"Yanan Wang\",\"Wen Li\",\"Yibin Ying\",\"Zhenghao Fei\"]","published":"2026-07-01T07:35:12Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}