A showcase of our post-training process, with web search and code execution built in.

X上の言説は、パクストン候補への評価の転変や宗教やデータセンターをめぐる両候補のナラティブとその評価など、世論調査には現れない複雑な動きを示していました。また、両候補者への評価の転換は、Cook Political Reportなどの主要評価機関が判断を変える約2か月前に現れていました。

We’re excited to introduce Doc-to-LoRA and Text-to-LoRA, two related research exploring how to make LLM customization faster and more accessible. By training a Hypernetwork to generate LoRA adapters ...

One of the grand challenges of artificial intelligence is developing agents capable of conducting scientific research and discovering new knowledge. While frontier models have already been used to aid ...

Excited to share our paper, “Learning Multi-Agent Coordination via Sheaf-ADMM” to be presented at ICML 2026. Most AI models process information as one giant, monolithic block. But in nature, ...

Standard language models process information as a rigid linear sequence where the only signal for structure is a fixed token index, forcing them to treat physical proximity as semantic relevance.

Sakana AI is a new AI research company based in Tokyo, Japan. Our founding team have proven track records of developing breakthroughs in AI, where we take pride in setting the trend in AI development.

For the past few years, humans have been doing “prompt engineering” to coax the best performance out of different LLMs. In this work, we explored what happens if we train an AI to do that job instead.

The next era of artificial intelligence will move beyond digital interfaces and directly into the physical world. To lead this paradigm shift, Sakana AI is incredibly proud to announce that Jürgen ...

Introducing “Scaling In-Context Imitation Learning” (SAIL) to be presented at IROS2026. This work is a collaboration between Sakana AI and the University of Tokyo. Teaching a robot something new ...

Following our 2024 research on evolutionary model merging, a technique for “mixing to create” better models from existing ones (left), we are now tackling the challenge of “mixing to use” frontier ...