Sakana AI· Sakana modelsResearch paper

Learning to Orchestrate Agents in Natural Language with the Conductor

Sakana AI announces a research paper accepted at ICLR2026 on a Conductor model trained with reinforcement learning to orchestrate multiple AI agents via natural language, achieving state-of-the-art results on LiveCodeBench and GPQA-Diamond. The research also powers a new multi-agent system called Sakana Fugu.

From the source

We trained a 7B Conductor model using Reinforcement Learning to orchestrate a pool of frontier models (including GPT-5, Gemini, Claude, and open-source models available during the period leading up to ICLR2026). ... This foundational research powers our new multi-agent system: Sakana Fugu ! 🐡

sakana.ai

Announced

26 Apr 2026 15:00 UTC

Detected

28 Aug 2026 21:48 UTC (+124d after)