ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution

We're incredibly excited to welcome Robert Tjarko Lange (Founding Research Scientist at Sakana.AI) for a talk on ShinkaEvolve, a new open-source framework leveraging large language models to advance scientific discovery with state-of-the-art performance and unprecedented efficiency.

ABSTRACT
Recent advances in scaling inference time compute of LLMs have enabled significant progress in generalized scientific discovery. These approaches rely on evolutionary agentic harnesses that leverage LLMs as mutation operators to generate candidate solutions. However, current code evolution methods suffer from critical limitations: they are sample inefficient, requiring thousands of samples to identify effective solutions, and remain closed-source, hindering broad adoption and extension. ShinkaEvolve addresses these limitations, introducing three key innovations: a parent sampling technique balancing exploration and exploitation, code novelty rejection-sampling for efficient search space exploration, and a bandit-based LLM ensemble selection strategy. We evaluate ShinkaEvolve across diverse tasks, demonstrating consistent improvements in sample efficiency and solution quality. ShinkaEvolve discovers a new state-of-the-art circle packing solution using only 150 samples, designs high-performing agentic harnesses for AIME mathematical reasoning tasks, identifies improvements to ALE-Bench competitive programming solutions, and discovers novel mixture-of-expert load balancing loss functions that illuminate the space of optimization strategies. Our results demonstrate that ShinkaEvolve achieves broad applicability with exceptional sample efficiency. Finally, ShinkaEvolve recently was able to support human programmers (team Unagi) in winning the 2025 ICFP Competitive Programming Contest by automatically optimizing SAT solver encodings.

Paper: https://arxiv.org/abs/2509.19349
Blog Post — Release: https://sakana.ai/shinka-evolve/
Blog Post — ICFP 25: https://sakana.ai/icfp-2025/
Code: https://github.com/SakanaAI/ShinkaEvolve
Tweet: https://x.com/SakanaAILabs/status/1971081557210489039

SPEAKER BIO
Rob is a Founding Research Scientist at Sakana.AI. Furthermore, he is a final-year PhD student working on Evolutionary Meta-Learning at the Technical University Berlin. Previously, he completed a MSc in Computing at Imperial College London, a Data Science MSc at Universitat Pompeu Fabra and an Economics undergraduate at University of Cologne. He worked at Google DeepMind with the Tokyo team as a full-time student researcher and interned at Legacy DeepMind (Discovery team) & Accenture and maintains a set of open source tools: evosax (JAX-based Evolution Strategies) and gymnax (JAX-based Reinforcement Learning Environments).

MLT QUICK LINKS
YouTube
Newsletter signup
Discord