# ASTREA: Introducing Agentic Intelligence for Orbital Thermal Autonomy

arXiv: https://arxiv.org/abs/2509.13380 · HTML: https://mlsanity.com/paper/2509.13380/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 14 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 6 of 6)

- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [An Empirical Study of Qwen3 Quantization](https://mlsanity.com/paper/2505.02214/) (2025)
- [The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learning](https://mlsanity.com/paper/2502.15214/) (2025)
- [HCRMP: A LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving](https://mlsanity.com/paper/2505.15793/) (2025)
- [Autonomous Payload Thermal Control](https://mlsanity.com/paper/2307.15438/) (2023)
- [AI Space Cortex: An Experimental System for Future Era Space Exploration](https://mlsanity.com/paper/2507.06574/) (2025)

## Built on by (most cited first, 2 of 2)

- [AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning Problems](https://mlsanity.com/paper/2601.11354/) (2026)
- [NAVI-Orbital: First In-Orbit Demonstration of a Zero-Shot Vision-Language Model for Autonomous Earth Observation](https://mlsanity.com/paper/2606.18271/) (2026)

## Abstract (arXiv)

This paper presents ASTREA, the first agentic system executed on flight-heritage hardware (TRL 9) for autonomous spacecraft operations, with on-orbit operation aboard the International Space Station (ISS). Using thermal control as a representative use case, we integrate a resource-constrained Large Language Model (LLM) agent with a reinforcement learning controller in an asynchronous architecture tailored for space-qualified platforms. Ground experiments show that LLM-guided supervision improves thermal stability and reduces violations, confirming the feasibility of combining semantic reasoning with adaptive control under hardware constraints. On-orbit validation aboard the ISS initially faced challenges due to inference latency misaligned with the rapid thermal cycles of Low Earth Orbit (LEO) satellites. Synchronization with the orbit length successfully surpassed the baseline with reduced violations, extended episode durations, and improved CPU utilization. These findings demonstrate the potential for scalable agentic supervision architectures in future autonomous spacecraft.