# Sakana AI — Trinity: An Evolved LLM Coordinator

- Company: Sakana AI (sakana.ai)
- Announced: 2026-04-25T15:00:00+00:00
- Category: research-paper
- Subject: Sakana models
- Models affected: GPT-5, Gemini 2.5-Pro, Claude-4-Sonnet
- Source: https://sakana.ai/trinity
- Record: https://forck.live/items/4687-trinity-an-evolved-llm-coordinator

Sakana AI announces a new paper, 'TRINITY: An Evolved LLM Coordinator', accepted at ICLR2026. The paper introduces a system that coordinates multiple LLMs by dynamically assigning roles (Thinker, Worker, Verifier) using a lightweight coordinator with fewer than 20K learnable parameters, trained via evolutionary algorithms. The system achieves state-of-the-art results on LiveCodeBench (86.2% pass@1) and generalizes zero-shot to unseen tasks, outperforming individual models including GPT-5, Gemini 2.5-Pro, and Claude-4-Sonnet.

## Evidence

Verbatim from https://sakana.ai/trinity:

> Excited to share our new paper: “TRINITY: An Evolved LLM Coordinator”, published as a conference paper at ICLR2026!

---

Record: https://forck.live/items/4687-trinity-an-evolved-llm-coordinator
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md