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

2025/06/20 by Besrour, Ines, He, Jingbo, Schreieder, Tobias +1 · 1 citation
Computer Science · #Expert finding and Q&A systems #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Information Retrieval and Search Behavior #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2506.16988

openalex publication_date 2025/06/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Generating Diverse Q&A Benchmarks for RAG Evaluation with DataMorgana
• Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition
• ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator
• IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues
• CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity
• Training Language Models to Generate Text with Citations via Fine-grained Rewards
• Enabling Large Language Models to Generate Text with Citations
• Benchmarking Large Language Models for News Summarization
• Text Embeddings by Weakly-Supervised Contrastive Pre-training
• Galactica: A Large Language Model for Science

Cited by

• SIGIR 2025 -- LiveRAG Challenge Report

Related

• SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation
• RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering
• Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
• Evaluating RAG-Fusion with RAGElo: an Automated Elo-based Framework
• SLA Management in Reconfigurable Multi-Agent RAG: A Systems Approach to Question Answering