A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces

Key points

Existing RAG paradigms that rely on a single retrieval step or a predefined workflow do not fully exploit the advanced reasoning and multi-step tool-use abilities of modern agentic LLMs.
Current RAG systems are static and rigid, which prevents the LLM from dynamically adjusting its retrieval strategy according to query nuance or the current state of information gathering.
The lack of agentic autonomy in traditional RAG limits scaling with LLM capability, because the model is not allowed to make intelligent retrieval decisions.
A-RAG builds a lightweight two-stage hierarchical index without large offline graph construction by splitting the corpus into semantically coherent chunks and embedding individual sentences for fine-grained matching.
The framework gives LLM agents three hierarchical retrieval interfaces: keyword search for exact lexical matching, semantic search for dense semantic similarity, and chunk reading for access to whole chunk content and nearby context.
Through a simple ReAct-like agent loop, the LLM repeatedly reasons and calls retrieval tools to decide what to retrieve, how to retrieve it, and when to stop, and a context tracker helps avoid redundant reading.

External research summaries. These are not HDATF publications or measured product results.