Tripling an LLM's ARC-AGI-2 score with code evolution (imbue.com) 17 points by danielmewes 4mo ago ↗ HN
[–] danielmewes 4mo ago ↗ Author here.We originally developed our evolution-inspired tool to optimize LLM prompts. To our surprise, we found that the same method also worked well for getting better performance out of a base model on ARC-AGI tasks.We're open-sourcing the evolver tool today. It is built to be adapted to many different optimization problems. (Some coding required) You can read more about it at https://imbue.com/research/2026-02-27-darwinian-evolver/Happy to answer questions!
2 comments
[ 5.4 ms ] story [ 12.3 ms ] threadWe originally developed our evolution-inspired tool to optimize LLM prompts. To our surprise, we found that the same method also worked well for getting better performance out of a base model on ARC-AGI tasks.
We're open-sourcing the evolver tool today. It is built to be adapted to many different optimization problems. (Some coding required) You can read more about it at https://imbue.com/research/2026-02-27-darwinian-evolver/
Happy to answer questions!