ai-driven-research

This blog post introduces LEVI, a framework for AI-driven research for systems (ADRS) that reduces the cost of algorithmic discovery by using smaller models for most mutations and reserving large models for paradigm shifts, achieving 3-7x cost reduction. It argues that ADRS should be integrated into CI/CD for continuous, bespoke optimization per deployment.

The paper introduces GAMBLe, a framework that decomposes AI-Driven Research Systems into generator, assessor, discovery mechanism, and budget, revealing how component interactions shape optimization landscapes. Experiments on NP-hard problems show no universally best configuration, emphasizing the need for careful component selection.