Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems
Quick summary
arXiv:2606.18837v3 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks. However, existing methods face a dilemma between model capability and experience retention. Inference-time MAS leverages frozen frontier LLMs but repeats identical searches without learning from past experience. Conversely, Training-time MAS internalizes experience via gradient updates but is constrained by the low capability ceiling of smaller models, and is hard to scale to large frontier LLMs. To b
Key takeaways
- arXiv:2606.18837v3 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks.
- However, existing methods face a dilemma between model capability and experience retention.
- Inference-time MAS leverages frozen frontier LLMs but repeats identical searches without learning from past experience.
Why it matters
“Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments