# Bridging Semantics and Geometry: A Decoupled LVLM-SAM Framework for Reasoning Segmentation in Optical Remote Sensing arXiv: https://arxiv.org/abs/2512.19302 ยท HTML: https://mlsanity.com/paper/2512.19302/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. - Builds on 21 of its 60 references that are in the map. - First posted on arXiv 22 Dec 2025. ## Placed in - LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/) ## Builds on (most cited first, 21 of 21) - [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017) - [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024) - [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025) - [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023) - [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024) - [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025) - [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025) - [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025) - [R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization](https://mlsanity.com/paper/2503.12937/) (2025) - [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025) - [Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement](https://mlsanity.com/paper/2503.06520/) (2025) - [LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model](https://mlsanity.com/paper/2312.17240/) (2023) - [EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model](https://mlsanity.com/paper/2406.20076/) (2024) - [VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning](https://mlsanity.com/paper/2505.12081/) (2025) - [GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding](https://mlsanity.com/paper/2411.11904/) (2024) - [Text2Seg: Remote Sensing Image Semantic Segmentation via Text-Guided Visual Foundation Models](https://mlsanity.com/paper/2304.10597/) (2023) - [SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model](https://mlsanity.com/paper/2504.09644/) (2025) - [RemoteSAM: Towards Segment Anything for Earth Observation](https://mlsanity.com/paper/2505.18022/) (2025) - [RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts](https://mlsanity.com/paper/2412.05679/) (2024) - [RemoteReasoner: Towards Unifying Geospatial Reasoning Workflow](https://mlsanity.com/paper/2507.19280/) (2025) - [Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2410.08613/) (2024) ## Built on by (most cited first, 6 of 6) - [WeaveEarth: Structured Evidence Construction and Reasoning for Training-Free UHR Remote Sensing Understanding](https://mlsanity.com/paper/2607.10120/) (2026) - [B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation](https://mlsanity.com/paper/2605.23500/) (2026) - [Adapting Open-Weight MLLMs to Generate Point Prompts for Electron Microscopy Segmentation](https://mlsanity.com/paper/2609.14080/) (2026) - [COCOTree: A Dataset and Benchmark for Open Tree-Structured Visual Decomposition](https://mlsanity.com/paper/2605.22068/) (2026) - [More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe](https://mlsanity.com/paper/2607.15942/) (2026) - [LLM-Driven Training-free Location-Attribute Synergic Fusion: A Closed-Loop Paradigm for Dual-source Encrypted POIs and LULC Mapping](https://mlsanity.com/paper/2609.25051/) (2026) ## Abstract (arXiv) Large Vision--Language Models (LVLMs) hold great promise for advancing optical remote sensing (RS) analysis, yet existing reasoning segmentation frameworks couple linguistic reasoning and pixel prediction through end-to-end supervised fine-tuning, leading to weak geometric grounding and limited generalization across tasks. To address this, we developed Think2Seg-RS, a decoupled framework that trains an LVLM prompter to control a frozen Segment Anything Model (SAM) via structured geometric prompts. Through a mask-only Group Relative Policy Optimization (GRPO) reinforcement learning objective driven strictly by final mask IoU, the LVLM learns to translate abstract semantic reasoning into spatially grounded actions, achieving state-of-the-art performance on the EarthReason dataset. Notably, Think2Seg-RS outperforms leading approaches such as RemoteReasoner and SegEarth-R1 on the EarthReason dataset by reaching a test cIoU of 75.60% and gIoU of 73.36%, yielding absolute improvements of 6.47% and 2.40% over the strongest baseline, respectively. Zero-shot evaluations across three referring segmentation benchmarks reveal a fundamental distinction in task inductive bias, exposing a distinct divide between semantic-level grounding -- which aggregates all regions matching a conceptual intent -- and instance-level tasks that demand discrete object separation. We further found that compact segmenters outperform larger ones under semantic-level supervision by mitigating textural over-segmentation, and that unconstrained negative prompting is unstable in heterogeneous aerial backgrounds. Together, these findings demonstrate that optimizing LVLMs through direct segmentation feedback offers a scalable framework for complex geospatial reasoning, effectively bridging the gap between abstract language understanding and precise pixel-level execution.