---
id: 20260925-T0-06
title: "COMED：多LLM推理中路由与协作之间的空白地带"
title_en: "COMED: Filling the Gap Between Routing and Collaboration in Multi-LLM Inference"
url: https://ai.daily.yangsir.net/daily/20260925-T0-06
issue_date: 2026-09-25
publish_date: 2026-09-24T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2609.26913
---

# COMED：多LLM推理中路由与协作之间的空白地带

arXiv发表论文COMED，针对多LLM推理系统提出新方案。现有系统要么在多个模型间进行路由选择，要么将多个模型的输出进行密集协作组合。但路由在选定初始模型后就停止，而密集协作则计算成本过高。COMED试图填补两者之间的空白，提供一种介于路由和协作之间的中间方案。对构建多模型推理系统的开发者而言，该方法可能在成本和效果之间提供更优的平衡点。

## English Version

**COMED: Filling the Gap Between Routing and Collaboration in Multi-LLM Inference**

A new arXiv paper introduces COMED, a method for multi-LLM inference systems. Existing approaches either route among models or densely combine their outputs. However, routing stops after selecting an initial model, while dense collaboration is computationally expensive. COMED aims to fill the missing middle between routing and collaboration. For developers building multi-model inference systems, this method may offer a better balance between cost and performance.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2609.26913)

**详情页**：https://ai.daily.yangsir.net/daily/20260925-T0-06

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*