Reproduce “Large Language Model-Assisted Adaptive Heuristic Search for Agile Earth Observation Satellite Scheduling” 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
He Wang, Yeye Liu, Ruijie Li, Xuemei Jiang, Junyu Wu, Lining Liu Zhuoqi Man, Tao Li, Yanjie Song
The authors present LLMACO, a satellite-scheduling method in which an LLM proposes and revises candidate-scoring rules while ant-colony search constructs feasible schedules. The rules rank observations subject to time-window, maneuver, and energy constraints. Across six simulated scenarios with 50–200 tasks, LLMACO achieved 4.32%–9.63% higher mean observation benefit than the strongest baseline; dynamic conditions remain untested.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.