Reproduce “Vulcan: Instance-specialized, Verifiable Systems Heuristics Through LLM-driven Search” 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

Rohit Dwivedula, Divyanshu Saxena, Sujay Yadalam, Eric Hayden Campbell, Daehyeok Kim, Aditya Akella

Vulcan lets an LLM search system-policy decisions while trusted developer code retains state management and system-facing behavior. Its Value and Rank interfaces use runtime features, and Anvil bounds generated programs, with safety guarantees conditional on linked functions. In spot scheduling, Vulcan averages $7.12 savings per job, versus $1.46 for UP and $4.31 for ADRS across 21,600 cases.

Summary by alphaXiv.

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