# Sakana AI — Learning to Orchestrate Agents in Natural Language with the Conductor

- Company: Sakana AI (sakana.ai)
- Announced: 2026-04-26T15:00:00+00:00
- Category: research-paper
- Subject: Sakana models
- Models affected: Conductor
- Source: https://sakana.ai/learning-to-orchestrate
- Record: https://forck.live/items/4686-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.

## Evidence

Verbatim from https://sakana.ai/learning-to-orchestrate:

> 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 ! 🐡

---

Record: https://forck.live/items/4686-learning-to-orchestrate-agents-in-natural-language-with-the-conductor
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md