Reproduce “ORCA: Onboard Reflective Collaborative Agents for Reliable Task Offloading in LEO Satellite Networks” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Yunxin Geng, Shengxiang Hao, Yichen Wu, Haotian Liu, Weiwei Jiang, Lu Cao, Han Meng, Yuxuan Pan and 1 more

ORCA checks satellite task-offloading outcomes and allows bounded correction instead of treating node selection as final. Its Perceive, Reason, Act, and Learn roles interpret tasks, rank visible candidates, commit to execution, and evaluate results. In a simulation of 60 satellites with tested neighbor failures, ORCA completed 46.53% of tasks, 8.12 percentage points above MADQN; this does not establish flight readiness.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.