---
title: "GRADE：通过门控路由与自适应深度实现高效多智能体推理"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.10836v1"
permalink: "https://feed.astralor.com/items/itm_77c14f4adcd8237d87f4f0a9"
published: "2026-07-12T16:58:21.000Z"
score: 81
channel: "ai"
tags: ["CoGRPO","GRADE","多智能体系统","热替换","自适应深度","门控路由"]
---

# GRADE：通过门控路由与自适应深度实现高效多智能体推理

## AI 点评

> 这篇论文对于研究多智能体协作和大模型推理效率的从业者来说很有价值。它提出了实用的门控机制和训练方法，并支持模型热替换，有望降低实际系统的部署成本。尤其是CoGRPO的无评论家训练思路，或可启发类似场景。

## 速览

本文提出GRADE，一种层级多智能体系统，通过四个轻量级学习门控协同控制智能体选择、层级深度、智能体间通信和分支剪枝。训练采用CoGRPO算法，无需评论家网络。在约170亿活跃参数下，GRADE在GSM8K、MMLUPro和GPQA上超越所有基线，并在MMLUPro上以一半计算量超越最强基线4.8分。论文还分析了各组件贡献，验证了逐智能体校准对安全热替换的必要性。

## 关键点

- GRADE通过四个门控机制动态选择智能体、控制推理深度、决定通信时机和剪枝分支。
- CoGRPO训练方法无需批评网络，适配多智能体层级结构。
- 在170亿活跃参数下，GRADE在多个基准上超越更强基线，计算效率翻倍。
- 逐智能体校准机制支持推理时热替换专家模型，无需重训练。

## 全文

Multi-agent ensembling multiplies active parameters and inference cost without answering three basic questions: which agents to consult, how deeply a query should traverse a hierarchy of agents, and when inter-agent communication is worth its cost. We present GRADE (Gated Routing and Adaptive Depth for Efficient Reasoning), a hierarchical multi-agent system in which four lightweight learned gates jointly govern agent selection, hierarchy depth, inter-agent communication, and branch pruning. Training uses CoGRPO (Collaborative Group-Relative Policy Optimization), a novel critic-free recipe that adapts GRPO to multi-agent hierarchies and assigns a shared advantage signal to every gate and agent that participated in a rollout. Agent models are drawn from a hot-swappable Expert Registry; per-agent calibration maps allow experts to be replaced at inference time without retraining. At $\sim$17B average active parameters, GRADE outperforms all baselines on GSM8K, MMLUPro, and GPQA, surpassing the strongest baseline by 4.8 points on MMLUPro at half the active compute. On AIME-2025, where model depth dominates, GRADE remains competitive to existing frameworks. Ablations isolate the hierarchy and masked cross-attention as the largest contributors to accuracy, and show that per-agent calibration is necessary for safe hot-swapping.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_77c14f4adcd8237d87f4f0a9