Sakana AI Launches Fugu Multi-Agent Model with Single API Call for Multiple LLMs

According to PANews, on June 22, Sakana AI launched Sakana Fugu, a multi-agent model that enables coordination of multiple large language models through a single API call. The flagship model, Fugu Ultra, dynamically schedules multiple LLMs to handle complex multi-step tasks and performs close to frontier models on code, research, and reasoning benchmarks. The company stated the system aims to reduce dependence on single AI vendors and enhance performance and AI sovereignty through model orchestration, applicable to research, code review, cybersecurity, and patent analysis.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments