QChunker: Learning Question-Aware Text Chunking for Domain RAG via Multi-Agent Debate

2026-03-12

AI Summary

This work addresses the limitations of traditional RAG systems, where text chunking often suffers from insufficient semantic coherence and suboptimal information granularity, thereby degrading generation quality. The authors propose a question-driven multi-agent debate framework that formulates chunking as a joint task of segmentation and knowledge completion. The framework integrates a question outline generator, a text segmenter, a completeness reviewer, and a knowledge completer, augmented by document-outline-guided multi-path sampling and a small-model capability transfer mechanism. To directly evaluate chunk quality, they introduce a novel metric, ChunkScore, and release a high-quality dataset comprising 45K annotated chunks. Extensive experiments across four heterogeneous domains demonstrate that the proposed method significantly enhances the logical coherence and informational richness of generated chunks, exhibiting strong generalization capabilities.

Technology Category

• Natural Language Processing: Syntax — Tagging, Chunking & Parsing
• Multiagent Systems: Agreement, Argumentation & Negotiation
• Knowledge Representation and Reasoning: Argumentation

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

The effectiveness upper bound of retrieval-augmented generation (RAG) is fundamentally constrained by the semantic integrity and information granularity of text chunks in its knowledge base. To address these challenges, this paper proposes QChunker, which restructures the RAG paradigm from retrieval-augmentation to understanding-retrieval-augmentation. Firstly, QChunker models the text chunking as a composite task of text segmentation and knowledge completion to ensure the logical coherence and integrity of text chunks. Drawing inspiration from Hal Gregersen's "Questions Are the Answer" theory, we design a multi-agent debate framework comprising four specialized components: a question outline generator, text segmenter, integrity reviewer, and knowledge completer. This framework operates on the principle that questions serve as catalysts for profound insights. Through this pipeline, we successfully construct a high-quality dataset of 45K entries and transfer this capability to small language models. Additionally, to handle long evaluation chains and low efficiency in existing chunking evaluation methods, which overly rely on downstream QA tasks, we introduce a novel direct evaluation metric, ChunkScore. Both theoretical and experimental validations demonstrate that ChunkScore can directly and efficiently discriminate the quality of text chunks. Furthermore, during the text segmentation phase, we utilize document outlines for multi-path sampling to generate multiple candidate chunks and select the optimal solution employing ChunkScore. Extensive experimental results across four heterogeneous domains exhibit that QChunker effectively resolves aforementioned issues by providing RAG with more logically coherent and information-rich text chunks.

Problem

• retrieval-augmented generation
• text chunking
• semantic integrity
• information granularity
• RAG

Innovation

• question-aware chunking
• multi-agent debate
• retrieval-augmented generation
• ChunkScore
• knowledge completion