Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks A mid-training «practice phase» that teaches small open-source LLMs how to evolve solutions. Finch-9B is the largest and strongest member of the Finch family — open-source LLMs evolution fine-tuned (EFT) to act as a stronger mutation operator inside evolutionary search. Built on Qwen3.5-9B and trained on the Finch Collection, it learns how to evolve a solution and shows the largest discovery gains in the family. State-of-the-art discovery systems put an LLM inside an evolutionary search scaffold — but the discovery know-how lives in the scaffold, and every new task starts from zero. Evolution Fine-Tuning (EFT) moves that behavior into the model by turning evolutionary search trajectories into supervision. EFT pays off most at scale, making Finch-9B the family’s top performer across held-out discovery tasks. — (Left) EFT acts as mid-training, boosting Finch’s discovery on the Erdős minimum-overlap problem under both test-time search and test-time learning. — (Right) On NP-hard competitive programming, Finch composes strategies learned across diverse domains, while the base model relies on a single…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: minnesotanlp
Теги: qwen3_5, image-text-to-text, evolution-fine-tuning, evolutionary-search, discovery, code-optimization, scientific-discovery, mutation-operator
Лайков: 3 | Загрузок: 101
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
