Year: 2026
Type: conference-paper
Abstract: Remote sensing has emerged as an important domain for multimodal large language models (MLLMs), where reliable understanding requires locating small, dense, and spatially subtle visual evidence.However, our diagnostic analysis shows that current MLLMs often fail because their reasoning is not grounded to the correct visual evidence, leading to wrongregion attention or missed task-relevant objects.To address this issue, we introduce RsEvi-8B, an evidence-aware remote sensing MLLM that reasons with parseable boundingbox-grounded evidence.To enable this capability, we construct RsEvi-248K, a largescale supervised dataset spanning VQA, visual grounding, object detection, object counting, and scene classification.The dataset provides verified bounding-box-grounded reasoning traces, where each intermediate visual claim is aligned with supporting evidence regions and filtered for both answer correctness and evidence faithfulness.To improve evidence-faithful reasoning, we further propose the evidence-aware GRPO, which uses an evidence verifier to regulate learning on generated evidence spans while preserving tasklevel outcome optimization.Extensive experiments across five remote-sensing task families show that RsEvi-8B improves the datasetbalanced average score by 17.15 points over Qwen3-VL-8B-Instruct, establishing explicit visual grounding as a key ingredient for reliable remote-sensing reasoning.
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W7224509986