arXiv cs.CL· Sijie Zhao, Zeqi Zhou, Heli Qi, Xuanchao Fu, Zhuo Zheng, Junshi Xia, Junjue Wang, Weihao Xuan, Naoto Yokoya·· 2 天前AI 评分60
把任意地球观测任务变成递归自我改进：智能体自主构建遥感模型
The Last Remote Sensing Model Built by Humans? Casting Any Earth Observation Task as Recursive Self-Improvement
AI 导读
arXiv 论文提出把任意可验证的地球观测任务拆成 harness 与 verifier 两部分，由通用编码智能体据此自行构建并递归改进 EO 模型。在覆盖光学、SAR 和多光谱时间序列的六个 EO 基准上，智能体构建的模型全部超过当前最优水平，其中土地覆盖制图仅用 11% 的训练标签。作者认为这确立了人类设计 harness 与 verifier、智能体构建模型的新范式。
正文 · 原文
Abstract:Earth observation (EO) models are still built by hand. For each new task, experts design a training recipe and tune it against a benchmark. We show that this loop can be handed to an agent. Any verifiable task can be cast as a harness and a verifier, where the harness defines what the agent may use and the verifier defines what counts as success. Every EO task can be made verifiable, through labeled benchmarks, independent sensors, physical models or the repeated observation of the same place. Given only these two components, a general-purpose coding agent builds the EO model and improves it recursively on its own outputs. Settings long treated as separate research problems, from learning with a handful of labels to adapting across domains, become choices of harness and verifier. On six EO benchmarks spanning optical, SAR and multispectral time-series imagery, with outputs that range from land-cover maps and ship instances to canopy heights and answers about large images, agent-built models surpass the state of the art on every one, and on land-cover mapping, they do so from 11% of the training labels. This establishes a new paradigm for EO, in which people design harnesses and verifiers and agents build the models, so EO models improve as agents do.
| Comments: | Ongoing project |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.18845 [cs.CV] |
| (or arXiv:2610.18845v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18845 arXiv-issued DOI via DataCite |
Submission history
From: Sijie Zhao [view email]
[v1]
Tue, 13 Oct 2026 17:57:51 UTC (354 KB)
[v2]
Thu, 15 Oct 2026 16:56:46 UTC (412 KB)
来源：arXiv cs.CL · arxiv.org