Sakana AI released Fugu, a multi-Agent orchestration framework that uses a "conductor model" to align and coordinate multiple LLMs (including Fable 5, the latest from AI21). The standout: Fugu can match the quality of a single frontier model by orchestrating multiple smaller models, at 1/3 the cost.
The technical details: Fugu has three components — (1) a "conductor model" (a 13B model trained specifically for orchestration); (2) a "worker pool" (a set of LLMs of various sizes and specializations); (3) a "task router" (decides which worker handles which sub-task). The conductor model dynamically plans the multi-Agent workflow, monitors progress, and re-plans when a worker fails.
The "alignment" highlight: the conductor model is trained with a "Fable 5 alignment" loss — i.e., the orchestration is explicitly trained to produce outputs that are aligned with Fable 5's quality. This means the orchestrated multi-Agent system can match Fable 5's quality without using Fable 5 itself.
The benchmark: on a set of complex reasoning tasks (math, code, multi-step planning), Fugu hits 87% of Fable 5's quality, at 1/3 the inference cost. The biggest win is on long-horizon tasks, where multi-Agent decomposition naturally parallelizes the work.
The bigger takeaway: "multi-Agent orchestration" is becoming a real alternative to "single mega-model." The Fugu paper is one of the first to demonstrate that a well-orchestrated multi-Agent system can match a frontier single model at significantly lower cost. The "conductor model" pattern is the right abstraction for this, and Sakana AI is positioning itself as a leader in this space.