All papers

Research/ ORBITAL ROBOTICS

OrbitWeaver: LLM Agent Planning with Simulation Feedback for Optically Interconnected Orbital GPU Clusters

Pengcheng Luo, Bowen Zhang

Preprint 2026/
Space × AIORBITAL ROBOTICS
Technique

Foundation Models & LLMstext match · Guidance, Dynamics & ControlarXiv: eess.SY

Indexed as

arXivcs.DC · cs.SY · eess.SY

Space-based data-center designs increasingly consider GPU computing formations connected by inter-satellite optical links. With limited neighboring connections, jobs assigned disjoint GPUs can still contend on shared relay paths. Rank placement and communication priorities jointly affect this contention and the readiness of downstream computation. We present OrbitWeaver, an offline large language model (LLM) agent planner that jointly optimizes rank placement and communication order. Guided by communication structure, execution dependencies, and simulation feedback, the agent constructs and refines plans that coordinate shared-link access with computation progress. This coordination reduces contention and dependency blocking, shortening mean job completion time (JCT). Simulation experiments on optically interconnected orbital GPU clusters show that OrbitWeaver reduces aggregate mean JCT by 6.2-33.5% relative to the state-of-the-art baselines CASSINI, Crux, and Symphony. These results demonstrate the value of LLM-guided planning for efficient concurrent computing in orbital GPU clusters.

Related papers

The 10 papers closest in meaning to this one, from embeddings of each title and abstract, with a small boost for shared missions and techniques.

Latest in ORBITAL ROBOTICS

See all →

Shortcuts

j / k
Next / previous paper
Enter
Open paper
a
Toggle abstract
s
Save to reading list
c
Copy BibTeX
?
Show shortcuts