# CORE-Seg: Reasoning-Driven Segmentation for Complex Lesions via Reinforcement Learning Source: [CORE-Seg: Reasoning-Driven Segmentation for Complex Lesions via Reinforcement Learning]() Collection index: [llms.txt]() Data updated: 2026-03-10T05:00:05.424Z Authors: Yuxin Xie, Yuming Chen, Yishan Yang, Yi Zhou, Tao Zhou, Zhen Zhao, Jiacheng Liu, Huazhu Fu Published: 2026-03-06T04:58:55.000Z ## Abstract Medical image segmentation is undergoing a paradigm shift from conventional visual pattern matching to cognitive reasoning analysis. Although Multimodal Large Language Models (MLLMs) have shown promise in integrating linguistic and visual knowledge, significant gaps remain: existing general MLLMs possess broad common sense but lack the specialized visual reasoning required for complex lesions, whereas traditional segmentation models excel at pixel-level segmentation but lack logical interpretability. In this paper, we introduce ComLesion-14K, the first diverse Chain-of-Thought (CoT) benchmark for reasoning-driven complex lesion segmentation. To accomplish this task, we propose CORE-Seg, an end-to-end framework integrating reasoning with segmentation through a Semantic-Guided Prompt Adapter. We design a progressive training strategy from SFT to GRPO, equipped with an adaptive dual-granularity reward mechanism to mitigate reward sparsity. Our Method achieves state-of-the-art results with a mean Dice of 37.06\\% (14.89\\% higher than the second-best baseline), while reducing the failure rate to 18.42\\%. Project Page: https://xyxl024.github.io/CORE-Seg.github.io/ ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Lesion Segmentation on ComLesion-14K 1.0 (test)](): Lesion Segmentation; ComLesion-14K 1.0 (test); Mean Dice (mDice): 37.06. ## Original sources and implementation [Original paper]() [PDF]()