# 单LLM驱动多智能体系统扩展行为研究

- 来源：elvis (@omarsar0)
- 发布时间：2026-06-02 23:05
- AIHOT 分数：50
- AIHOT 链接：https://aihot.virxact.com/items/cmpws1c4f006qsl795bmem30w
- 原文链接：https://x.com/omarsar0/status/2061826427461464405

## AI 摘要

研究探讨添加更多智能体是否提升多智能体系统性能。结论指出，最优智能体数量取决于基础模型的能力和任务类型，而非单纯增加数量。集体智能更可能源于精心的交互设计，而非智能体数量的增多。相关论文："Scaling Behavior of Single LLM-Driven Multi-Agent Systems"。

## 正文

// Scaling Behavior of Single LLM-Driven Multi-Agent Systems //

Does adding more agents actually make a multi-agent system better？

It's possible that collective intelligence emerges from interaction design rather than from agent plurality.

This is something important to understand if you are building multi-agent systems.

This new study reports that the optimal number of agents depends on the base model's capability and the task type， not on adding more of them.

Paper： https://arxiv.org/abs/2606.00655

Learn to build effective AI agents in our academy： https://academy.dair.ai/