# SAT-Edge-Agent: Hardware-in-the-Loop Edge-Agent Orchestration for Onboard Satellite Intelligence

arXiv: https://arxiv.org/abs/2608.03728 · HTML: https://mlsanity.com/paper/2608.03728/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 10 of 10)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2103.05569/) (2021)
- [Satellite edge computing for real-time and very-high resolution Earth observation](https://mlsanity.com/paper/2212.12912/) (2022)
- [Fast model inference and training on-board of Satellites](https://mlsanity.com/paper/2307.08700/) (2023)
- [Benchmarking Edge AI Platforms for High-Performance ML Inference](https://mlsanity.com/paper/2409.14803/) (2024)
- [Oriented object detection in optical remote sensing images using deep learning: a survey](https://mlsanity.com/paper/2302.10473/) (2023)
- [Advancing Earth Observation: A Survey on AI-Powered Image Processing in Satellites](https://mlsanity.com/paper/2501.12030/) (2025)
- [Beyond detection: cooperative multi-agent reasoning for rapid onboard EO crisis response](https://mlsanity.com/paper/2603.19858/) (2026)

## Abstract (arXiv)

Onboard satellite intelligence requires a task layer that translates mission intent into local tool calls, exposes execution state, and returns machine-consumable artifacts under communication and power constraints. We present SAT-Edge-Agent, a hardware-in-the-loop (HIL) edge-agent system deployed on a commercial off-the-shelf ARM-based heterogeneous edge system-on-chip. A browser workspace and FastAPI agent coordinate a local OpenAI-compatible language service with a project-internal YOLO-style oriented-object-detection endpoint that returns FAIR1M metadata-backed structured results. Two fixed FAIR1M workloads, one single-image and one serial two-image request, were repeated 20 times each and completed 20/20 attempts. Mean Full-Agent latency was 29.353 s and 60.937 s, with empirical P95 values of 31.166 s and 66.882 s. Mean detector time was 861.386 ms and 1510.920 ms, only 2.93% and 2.48% of the corresponding Full-Agent means. Profiling indicates that most visible latency occurs outside detector execution. Mean CPU utilization was 20.761% and 20.482%. A 200-ms NPU-load field averaged 100% for both workloads, but it represents a shared-accelerator software field rather than detector-only occupancy or calibrated utilization. The public evidence package provides sanitized request-level records, redacted JSON, normalized SSE examples, and scripts reproducing the reported statistics. These results establish a reproducible HIL boundary for observable satellite edge-agent orchestration, but do not establish detector accuracy, a new geolocation method, calibrated energy efficiency, or flight readiness.