Metraipolis › archive › dc_0c2eae71059c
SimCRAFT: Distilling Remote Sensing Agents via Synthetic Trajectories and Contextual Retrieval-Augmented Fine-Tuning — arXiv:2608.30277
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.30277
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:41:00.946Z
- SHA-256 of the archived text
0603dc89d608ae04dd28b70af95da240b4e15e1ac9e8b91fde5dbd88bb951fde- Stable URL of this page
https://metraipolis.com/documento/dc_0c2eae71059c
How to cite
SimCRAFT: Distilling Remote Sensing Agents via Synthetic Trajectories and Contextual Retrieval-Augmented Fine-Tuning — arXiv:2608.30277 — arXiv (en), https://arxiv.org/abs/2608.30277 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0c2eae71059c (Metraipolis archive dc_0c2eae71059c, sha256 0603dc89d608ae04dd28b70af95da240b4e15e1ac9e8b91fde5dbd88bb951fde)
BibTeX
@misc{dc0c2eae71059c,
title = {SimCRAFT: Distilling Remote Sensing Agents via Synthetic Trajectories and Contextual Retrieval-Augmented Fine-Tuning — arXiv:2608.30277},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.30277},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0c2eae71059c; sha256 0603dc89d608ae04dd28b70af95da240b4e15e1ac9e8b91fde5dbd88bb951fde},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30277. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The unprecedented surge in Earth observation data volume and diversity has exposed a critical bottleneck for traditional manual workflows, catalyzing the emergence of Remote Sensing (RS) Agents. However, the practical deployment of these advanced agents is severely hindered by their heavy reliance on large-scale general-purpose LLMs, which lack deep domain expertise and impose prohibitive infrastructure demands. To resolve this, we propose SimCRAFT, a model-agnostic framework that distills sophisticated RS orchestration capabilities into a compact 7B-scale model. Addressing data scarcity, we first pair a multiagent synthesis engine with a Mock Execution Engine that checks schema correctness, inter-tool dependencies, and sensor/tool compatibility, producing SimRS-14k, a large-scale, constraint-validated workflow planning corpus. Second, we propose Contextual Retrieval-Augmented Fine-Tuning (CRAFT) that finetunes the model to reason analogically by adapting retrieved Standard Operating Procedures to novel queries under a noise-robust objective, generalizing RAFT to multi-step RS workflow planning without mechanical copying. Extensive experiments demonstrate that SimCRAFT-7B significantly outperforms openweights LLMs and rivals advanced closedsource models and specialized RS agents, while reproducing across three 7B backbones. This work contributes a competitive open-weights baseline for lightweight RS intelligence, enabling efficient autonomous deployment under resource-constrained or resource-conserving conditions. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.MA). Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2608.30277 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T07:27:42.012Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).