A researcher used an LLM to iteratively evolve an optimization algorithm, improving the 10 best-known circle-packing solutions for the Packomania csqv problem across N=101 to N=114. The LLM proposed algorithmic changes guided by a scoreboard and history, with each candidate scored by an independent verifier.
I used an LLM to iteratively evolve an optimization algorithm rather than solve the packing directly. Starting from a simple seed solver, the LLM proposes algorithmic changes guided by a scoreboard of results and a history of prior attempts, and each candidate is scored by an independent verifier so
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.