AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Foundation Model Selection for Remote Sensing via a Constraint-Aware Agent

Binger Chen, Tacettin Bök, Behnood Rasti, Volker Markl, Begüm Demir

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add task-aware orchestration with multi-turn clarification over naive sequential tool use (ablation)Remsa-Naive · RS-FMD selection benchmark (GPT-4.1)Avg Top-1 score: 72.67 -> 75.76Improved
add task-aware orchestration over naive tool use (ablation)Remsa-Naive · RS-FMD selection benchmark (GPT-4.1)MRR: 0.29 -> 0.34Improved
add task-aware orchestration over naive tool use (ablation)Remsa-Naive · RS-FMD selection benchmark (GPT-4.1)HQ Hit Rate (%): 37.33% -> 40.00%Improved
add LLM ranking and constraint reasoning to retrieval-only (ablation)DB-Retrieval · RS-FMD selection benchmark (GPT-4.1)Top-1 Hit Rate (%): 12.00% -> 21.33%Improved
add LLM ranking and constraint reasoning to retrieval-only (ablation)DB-Retrieval · RS-FMD selection benchmark (GPT-4.1)HQ Hit Rate (%): 17.33% -> 40.00%Improved
add structured schema grounding over unstructured RAG (ablation)Unstr.-RAG · RS-FMD selection benchmark (GPT-4.1)Top-1 Hit Rate (%): 13.33% -> 21.33%Improved
use Remsa on DeepSeek3.2 backbone versus naive orchestration (ablation)Remsa-Naive · RS-FMD selection benchmark (DeepSeek3.2)Avg Top-1 score: 72.03 -> 75.35Improved
use Remsa on LLaMA-3.3-70B backbone versus naive orchestration (ablation)Remsa-Naive · RS-FMD selection benchmark (LLaMA-3.3-70B)Avg Top-1 score: 69.02 -> 73.39Improved
swap backbone from GPT-4.1 to LLaMA-3.3-70BRemsa · RS-FMD selection benchmark (GPT-4.1)Avg Top-1 score: 75.76 -> 73.39Hurt
swap backbone from GPT-4.1 to DeepSeek3.2Remsa · RS-FMD selection benchmark (GPT-4.1)Avg Top-1 score: 75.76 -> 75.35No clear effect
add multi-stage orchestration (latency cost)Remsa-Naive · RS-FMD selection benchmark (GPT-4.1)latency per query (s): 22.7s -> 31.7sHurt
include Application Compatibility criterion in scoring (ablation)rubric · RS-FMD criteria sensitivityAvg Set score: 73.32 -> 75.03Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy