# Sakana AI — Population-based Model Merging via Quality Diversity

- Company: Sakana AI (sakana.ai)
- Announced: 2024-12-02T16:10:00+00:00
- Category: research-paper
- Subject: Sakana models
- Source: https://sakana.ai/cycleqd
- Record: https://forck.live/items/4727-population-based-model-merging-via-quality-diversity

Sakana AI presents CycleQD, a framework for evolving a population of small LLM agents (8B parameters) using model merging and quality diversity to excel in agentic tasks, supported by the Japanese GENIAC grant.

## Evidence

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

> We explore this concept in our recent paper, Agent Skill Acquisition for Large Language Models via CycleQD , where we propose a framework called CycleQD for evolving a swarm of LLM agents, each with their own niche, to tackle difficult agentic workflow tasks.

---

Record: https://forck.live/items/4727-population-based-model-merging-via-quality-diversity
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md