RAGentA: Multi-Agent Retrieval-Augmented Generation for Attributed Question Answering

TL;DR

RAGentA introduces a multi-agent retrieval-augmented framework for attributed question answering, enhancing answer correctness and faithfulness through iterative filtering, hybrid retrieval, and document verification, leading to improved performance over standard baselines.

Contribution

The paper proposes a novel multi-agent RAG framework with hybrid retrieval and iterative refinement to improve trustworthy answer generation in attributed QA tasks.

Findings

Recall@20 improved by 12.5% with hybrid retrieval

Achieved 1.09% higher correctness over baselines

Achieved 10.72% higher faithfulness in answers

Abstract

We present RAGentA, a multi-agent retrieval-augmented generation (RAG) framework for attributed question answering (QA) with large language models (LLMs). With the goal of trustworthy answer generation, RAGentA focuses on optimizing answer correctness, defined by coverage and relevance to the question and faithfulness, which measures the extent to which answers are grounded in retrieved documents. RAGentA uses a multi-agent architecture that iteratively filters retrieved documents, generates attributed answers with in-line citations, and verifies completeness through dynamic refinement. Central to the framework is a hybrid retrieval strategy that combines sparse and dense methods, improving Recall@20 by 12.5% compared to the best single retrieval model, resulting in more correct and well-supported answers. Evaluated on a synthetic QA dataset derived from the FineWeb index, RAGentA outperforms standard RAG baselines, achieving gains of 1.09% in correctness and 10.72% in faithfulness. These results demonstrate the effectiveness of our multi-agent RAG architecture and hybrid retrieval strategy in advancing trustworthy QA with LLMs.