top | item 47185163 Tripling an LLM's ARC-AGI-2 score with code evolution 17 points| danielmewes | 3 days ago |imbue.com 2 comments order hn newest danielmewes|3 days 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! mrtibbets|3 days ago Clean breakdown. The reasoning vs scaling framing makes sense.
danielmewes|3 days 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!
danielmewes|3 days ago
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!
mrtibbets|3 days ago