MAO-ARAG: Multi-Agent Orchestration for Adaptive Retrieval-Augmented Generation

TL;DR

MAO-ARAG introduces a multi-agent orchestration framework for retrieval-augmented generation that dynamically adapts workflows per query, balancing answer quality, cost, and latency through reinforcement learning.

Contribution

This paper presents the first adaptive RAG system using multi-agent orchestration and reinforcement learning to optimize workflows for diverse queries.

Findings

Achieves high answer quality across multiple QA datasets.

Maintains cost and latency within acceptable limits.

Demonstrates the effectiveness of multi-agent planning in RAG systems.

Abstract

In question-answering (QA) systems, Retrieval-Augmented Generation (RAG) has become pivotal in enhancing response accuracy and reducing hallucination issues. The architecture of RAG systems varies significantly, encompassing single-round RAG, iterative RAG, and reasoning RAG, each tailored to address different types of queries. Due to the varying complexity of real-world queries, a fixed RAG pipeline often struggles to balance performance and cost efficiency across different queries. To address this challenge, we propose an adaptive RAG framework called MAO-ARAG, which leverages multi-agent orchestration. Our adaptive RAG is conceived as a multi-turn framework. Specifically, we define multiple executor agents, representing typical RAG modules such as query reformulation agents, document selection agent, and generation agents. A planner agent intelligently selects and integrates the appropriate agents from these executors into a suitable workflow tailored for each query, striving for high-quality answers while maintaining reasonable costs. During each turn, the planner agent is trained using reinforcement learning, guided by an outcome-based reward (F1 score) and a cost-based penalty, continuously improving answer quality while keeping costs within a reasonable range. Experiments conducted on multiple QA datasets demonstrate that our approach, which dynamically plans workflows for each query, not only achieves high answer quality but also maintains both cost and latency within acceptable limits.The code of MAO-ARAG is on https://github.com/chenyiqun/Agentic-RAG.