Recent advances in reasoning language models and reinforcement learning with verifiable rewards have significantly enhanced multi-step reasoning capabilities. This progress motivates the extension of reasoning paradigms to remote sensing visual grounding task. However, existing remote sensing grounding methods remain largely confined to perception-level matching and single-entity formulations, limiting the role of explicit reasoning and inter-entity modeling. To address this challenge, we introduce a new benchmark dataset for Multi-Entity Reasoning Grounding in Remote Sensing (ME-RSRG). Based on ME-RSRG, we reformulate remote sensing grounding as a multi-entity reasoning task and propose an Entity-Aware Reasoning (EAR) framework built upon visual-linguistic foundation models. EAR generates structured reasoning traces and subject-object grounding outputs. It adopts supervised fine-tuning for cold-start initialization and is further optimized via entity-aware reward-driven Group Relative Policy Optimization (GRPO). Extensive experiments on ME-RSRG demonstrate the challenges of multi-entity reasoning and verify the effectiveness of our proposed EAR framework. Our dataset, code, and models will be available at https://github.com/CV-ShuchangLyu/ME-RSRG.
@article{arxiv.2603.12788,
title = {Think and Answer ME: Benchmarking and Exploring Multi-Entity Reasoning Grounding in Remote Sensing},
author = {Shuchang Lyu and Haiquan Wen and Guangliang Cheng and Meng Li and Zheng Zhou and You Zhou and Dingding Yao and Zhenwei Shi},
journal= {arXiv preprint arXiv:2603.12788},
year = {2026}
}