Research
Learning to Orchestrate Agents in Natural Language with the Conductor Fugu Blog: https://sakana.ai/fugu-beta Paper: https://arxiv.org/abs/25…
Conductor is a method for orchestrating multiple AI agents through natural language instructions, enabling coordinated multi-agent systems where a central 'conductor' agent directs specialized agents
Conductor is a method for orchestrating multiple AI agents through natural language instructions, enabling coordinated multi-agent systems where a central "conductor" agent directs specialized agents to collaborate on complex tasks. The approach allows for flexible, language-based control of agent interactions without requiring explicit programming of agent coordination logic. This work was developed by Sakana AI and addresses the challenge of scaling AI systems by leveraging natural language as an interface for multi-agent collaboration.
Related
- TRINITY: An Evolved LLM Coordinator https://arxiv.org/abs/2512.04695
- Introducing our new work: “Learning to Orchestrate Agents in Natural Language with the Conductor” accepted at #ICLR2026 https://arxiv.org/ab…
- One of my favorite things about Sakana Fugu is the recursive test-time scaling. When allowed to call itself recursively, it reads its own pr…
Source: David Ha (X) | 2026-04-28