AtomRAG: atomic query decomposition for multi-hop retrieval-augmented generation
Academia AI and Applications · 16.04.2026 · 2 (2)
DOI: 10.20935/acadai8242 ↗Kurz gefasst
Fachartikel in der Zeitschrift Academia AI and Applications, online erschienen am 16.04.2026. Verfasst von Nikita Igolnikov und 1 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben.
Abstract (Originalsprache)
Introduction
Standard Retrieval-Augmented Generation (RAG) often fails on multi-hop queries that require the synthesis of information from multiple sources. To address this limitation, we propose AtomRAG, a chain-of-prompts algorithm that decomposes a complex query into a series of atomic requirements for information retrieval. Materials and methods: This method utilizes a sequence of planning, parsing, and reasoning prompts to guide a large language model (LLM) in creating an explicit retrieval and synthesis plan before generating a final answer. We evaluated AtomRAG on FRAMES and BRIGHT benchmarks, comparing its performance against standard RAG and non-RAG baselines using an instruction-tuned model (Meta-Llama-3.1-8B-Instruct) and a reasoning model (DeepSeek-R1-Distill-Llama-8B).
Results
Our results reveal a significant performance divergence. For the instruction-tuned model, AtomRAG improved accuracy by a relative 14.8% on the complex reasoning tasks in FRAMES. Conversely, the reasoning model proved incompatible with the instructive planning prompts, resulting in a performance degradation. On the less complex BRIGHT benchmark simpler methods performed better.
Conclusions
We conclude that the effectiveness of AtomRAG is highly dependent on both query complexity and model architecture.
Zitieren
APA
Igolnikov, N., & Abbas, N. (2026). AtomRAG: atomic query decomposition for multi-hop retrieval-augmented generation. Academia AI and Applications, 2(2). https://doi.org/10.20935/acadai8242
Vancouver
Igolnikov N, Abbas N. AtomRAG: atomic query decomposition for multi-hop retrieval-augmented generation. Academia AI and Applications. 2026;2(2). doi:10.20935/acadai8242
BibTeX
@article{Igolnikov2026,
author = {Igolnikov, Nikita and Abbas, Noorhan},
title = {AtomRAG: atomic query decomposition for multi-hop retrieval-augmented generation},
journal = {Academia AI and Applications},
year = {2026},
volume = {2},
number = {2},
doi = {10.20935/acadai8242}
}
EUVIMED