weird machine
Twenty-Eight Dollars Bought Ten Circle-Packing Records
An LLM-guided optimization loop improved ten accepted Packomania results in 15 iterations, with an independent verifier keeping only valid gains.
Summary
An LLM-guided optimization loop improved ten accepted Packomania results in 15 iterations, with an independent verifier keeping only valid gains.
Discovery Loop starts with a simple solver, asks a language model to propose algorithmic changes, scores each candidate with an independent verifier and retains only improvements. Applied to a variable-radius circle-packing benchmark, the system improved the best known solutions for ten values of N between 101 and 114 by 2.4 to 5.4 percent. The run took 15 iterations and $27.72 in reported model cost, and the results were accepted by Packomania. This is a narrow optimization result, but it shows how inexpensive search can matter when claims are checked by a deterministic judge.
Why it matters
An LLM-guided optimization loop improved ten accepted Packomania results in 15 iterations, with an independent verifier keeping only valid gains.
Limits and context
- Discovery Loop starts with a simple solver, asks a language model to propose algorithmic changes, scores each candidate with an independent verifier and retains only improvements.
Key claims
An LLM-guided optimization loop improved ten accepted Packomania results in 15 iterations, with an independent verifier keeping only valid gains.
Qualification: Discovery Loop starts with a simple solver, asks a language model to propose algorithmic changes, scores each candidate with an independent verifier and retains only improvements.
Evidence: source-2026-09-08-008
Sources
- arXiv preprint 2609.05093arXiv · primary research
Corrections
No corrections have been recorded for this story.