---
title: "ProgRouter：面向质量-成本权衡的多智能体LLM工作流在线进度引导路由"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.25992v1"
permalink: "https://feed.astralor.com/items/itm_e258b40d9736b6fc7af3877e"
published: "2026-08-26T16:42:02.000Z"
score: 71
channel: "ai"
tags: ["ProgRouter","任务进度评分","多智能体LLM工作流","成本优化","级联路由"]
---

# ProgRouter：面向质量-成本权衡的多智能体LLM工作流在线进度引导路由

## AI 点评

> 这篇论文的价值在于它不仅指出了级联路由的静态局限，还给出了可实操的在线分步路由方案。对正在将多智能体AI落地到生产环境的工程团队来说，ProgRouter提供了一条在不牺牲任务质量的前提下控制token成本的新路径。我也比较期待它的代码开源后在实际工作流中的表现。

## 速览

ProgRouter提出在线进度引导的路由框架，解决多智能体LLM工作流中质量与成本的动态权衡问题。现有级联路由仅做一次性查询级决策，难以适应多步骤任务的实时状态变化。ProgRouter通过多视图进度评分器融合子任务完成度、进度趋势与状态质量，借助双路径预测器与自适应元门控机制评估候选LLM的进度增益，实现分步在线路由。在HumanEval Plus、MBPP、MATH-500和ASQA上的实验显示，它在保持任务性能的同时显著降低运营成本。

## 关键点

- ProgRouter以实现质量-成本权衡下的在线进度引导式路由为核心，突破级联路由的静态决策范式。
- 多视图进度评分器融合子任务完成度、进度趋势与工作流状态质量，提供精细的进度感知。
- 双路径进度预测器与自适应元门控机制结合，可对每个候选LLM的进度增益进行在线估算。
- 在HumanEval Plus、MBPP、MATH-500与ASQA上的实验显示，运营成本显著下降且性能保持。

## 全文

Multi-agent large language model (LLM) workflows have emerged as a powerful paradigm for solving complex, open-ended tasks through collaborative reasoning among specialized LLM agents, but they incur substantial operating costs due to repeated LLM invocations and long-horizon context accumulation. Existing cascade routing methods make one-shot, query-level decisions and cannot adapt to the dynamic, state-dependent nature of multi-step workflows, in which the right LLM at each step depends on evolving task progress, remaining task difficulty, and cost-efficiency requirements. We present ProgRouter, an online progress-guided routing framework that adaptively selects LLM agents across workflow steps to preserve task-solving quality while adhering to time and cost budgets. ProgRouter introduces a multi-view task progress scorer that combines coarse workflow outcome regimes with fine-grained signals on subtask completion, progress trends, and workflow state quality. Then, a dual-path task progress predictor and an adaptive meta-gating mechanism estimate the progress gain for each candidate routed LLM. ProgRouter makes online step-wise routing decisions that balance progress gain, task time budgets, and long-term operating cost efficiency. Experiments on HumanEval Plus, MBPP, MATH-500, and ASQA, spanning agentic code generation, mathematical reasoning, and retrieval-augmented long-form question answering, demonstrate that ProgRouter reduces the operating cost relative to key baselines while maintaining strong task-solving performance.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_e258b40d9736b6fc7af3877e