# TerraAgent: Demonstration-Grounded Multi-Agent Reasoning for Long-Context Remote Sensing Visual Question Answering arXiv: https://arxiv.org/abs/2610.12517 ยท HTML: https://mlsanity.com/paper/2610.12517/ ## Key facts - No citing papers in the map yet (data through 14 Oct 2026). - Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. - Builds on 28 of its 36 references that are in the map. - First posted on arXiv 7 Oct 2026. ## Placed in - LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/) - Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/) - LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/) ## Builds on (most cited first, 28 of 28) - [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023) - [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023) - [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023) - [MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning](https://mlsanity.com/paper/2310.09478/) (2023) - [Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models](https://mlsanity.com/paper/2403.18814/) (2024) - [Reasoning with Language Model Prompting: A Survey](https://mlsanity.com/paper/2212.09597/) (2022) - [MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text](https://mlsanity.com/paper/2210.02928/) (2022) - [RSVQA: Visual Question Answering for Remote Sensing Data](https://mlsanity.com/paper/2003.07333/) (2020) - [LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model](https://mlsanity.com/paper/2402.02544/) (2024) - [Visual In-Context Learning for Large Vision-Language Models](https://mlsanity.com/paper/2402.11574/) (2024) - [VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding](https://mlsanity.com/paper/2406.12384/) (2024) - [Retrieval Augmented Visual Question Answering with Outside Knowledge](https://mlsanity.com/paper/2210.03809/) (2022) - [Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models](https://mlsanity.com/paper/2410.19732/) (2024) - [MAM: Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration](https://mlsanity.com/paper/2506.19835/) (2025) - [Retrieval-augmented Image Captioning](https://mlsanity.com/paper/2302.08268/) (2023) - [Distilled Dual-Encoder Model for Vision-Language Understanding](https://mlsanity.com/paper/2112.08723/) (2021) - [GATEAU: Selecting Influential Samples for Long Context Alignment](https://mlsanity.com/paper/2410.15633/) (2024) - [A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks](https://mlsanity.com/paper/2510.05608/) (2025) - [Long Context Question Answering via Supervised Contrastive Learning](https://mlsanity.com/paper/2112.08777/) (2021) - [RSAdapter: Adapting Multimodal Models for Remote Sensing Visual Question Answering](https://mlsanity.com/paper/2310.13120/) (2023) - [Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning](https://mlsanity.com/paper/2505.16483/) (2025) - [Remote Sensing Retrieval-Augmented Generation: Bridging Remote Sensing Imagery and Comprehensive Knowledge with a Multi-Modal Dataset and Retrieval-Augmented Generation Model](https://mlsanity.com/paper/2504.04988/) (2025) - [AVION: Aerial Vision-Language Instruction from Offline Teacher to Prompt-Tuned Network](https://mlsanity.com/paper/2603.12659/) (2026) - [Decoding the Delta: Unifying Remote Sensing Change Detection and Understanding with Multimodal Large Language Models](https://mlsanity.com/paper/2604.14044/) (2026) - [RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-N Ranking](https://mlsanity.com/paper/2604.20623/) (2026) - [Geospatial-Temporal Sensemaking of Remote Sensing Activity Detections with Multimodal Large Language Model](https://mlsanity.com/paper/2605.10739/) (2026) - [Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System](https://mlsanity.com/paper/2608.11738/) (2026) - [DamageScope: Vision-Language Retrieval at Scale for Disaster Damage Assessment from Satellite Imagery](https://mlsanity.com/paper/2608.21529/) (2026) ## Abstract (arXiv) Remote sensing visual question answering (RS-VQA) requires answers that truly depend on image evidence, yet current remote sensing multimodal large language models (RS MLLMs) are still evaluated mainly by accuracy, which cannot reveal whether a correct answer was produced without using the image. This setting introduces three challenges: demonstrations retrieved across different ground sample distances (GSD), sensors, and city textures may be poorly matched; real queries often involve long visual contexts from multi-scale tiles, multi-temporal frames, and retrieved knowledge, where evidence can be diluted and errors can propagate through multi-step reasoning; and prior-only answering remains invisible to standard metrics. We present AVA, a training-free framework that wraps a frozen RS MLLM with three modules. GDR performs GSD-bucketed, scene-graph-based demonstration retrieval and filters demonstrations whose answers are unsupported by their images. MACE decomposes each query into an evidence-typed sub-question DAG, routes sub-questions to suitable perception tools, and records verified provenance in a shared evidence ledger with bounded re-perception. CVA audits the final answer through counterfactual perturbations of cited evidence, including ablation and swap, and computes a visual-dependency score for confidence calibration and evidence-forcing re-query. On RSVQA-LR/HR, VRSBench, and LHRS-Bench, AVA improves average accuracy by up to 2.40 points over the strongest same-setting baselines, raises the visual-dependency score from 0.28 to 0.49, reduces the prior-only answer rate from 46.2 percent to 21.7 percent, and lowers the hallucination rate from 17.1 percent to 9.8 percent, with 2.6x the cost of a single backbone forward pass and no fine-tuning.