mlsanityData to 14 Oct 2026

ASTREA: Introducing Agentic Intelligence for Orbital Thermal Autonomy

arXiv 2509.13380 ↗First posted 16 Sep 2025cs.RO cs.AI cs.LGcited by 2

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

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.

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.

Builds on

6 of 14 references.

References · 6

  1. 2024Qwen2 Technical Reportcited by 2,120
  2. 2025An Empirical Study of Qwen3 Quantizationcited by 21
  3. 2025The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learningcited by 10
  4. 2025HCRMP: A LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Drivingcited by 4
  5. 2023Autonomous Payload Thermal Controlcited by 1
  6. 2025AI Space Cortex: An Experimental System for Future Era Space Explorationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning Problemscited by 1
  2. 2026NAVI-Orbital: First In-Orbit Demonstration of a Zero-Shot Vision-Language Model for Autonomous Earth Observationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024LLMSat: A Large Language Model-Based Goal-Oriented Agent for Autonomous Space Exploration
  2. 2026SpaceMind: A Modular and Self-Evolving Embodied Vision-Language Agent Framework for Autonomous On-orbit Servicing
  3. 2026Agentic AutoResearch forSpace Autonomy: An Auditable, LLM-Driven Research Agent for Aerospace Control Problems
  4. 2026GUIDE: Guided Updates for In-context Decision Evolution in LLM-Driven Spacecraft Operations
  5. 2024Fine-tuning LLMs for Autonomous Spacecraft Control: A Case Study Using Kerbal Space Program
  6. 2026Can LLMs Do Rocket Science? Exploring the Limits of Complex Reasoning with GTOC 12
  7. 2026OrbitTAMP: Grounding Language Models for Task and Motion Planning in Spacecraft Rendezvous
  8. 2026On-Orbit Space AI: Federated, Multi-Agent, and Collaborative Algorithms for Satellite Constellations