Queryome: orchestrating retrieval, reasoning, and synthesis across biomedical literature.
4 affiliations
- 1Department of Biological Sciences, Purdue University, West Lafayette, IN, 47906, USA.
- 2Department of Computer Science, Purdue University, West Lafayette, IN, 47906, USA.
- 3Department of Biological Sciences, Purdue University, West Lafayette, IN, 47906, USA. [email protected].
- 4Department of Computer Science, Purdue University, West Lafayette, IN, 47906, USA. [email protected].
Abstract
Background
The rapid expansion of biomedical literature has made comprehensive manual synthesis increasingly difficult, creating a pressing need for AI systems capable of reasoning over verified evidence rather than merely retrieving it. Existing retrieval-augmented generation (RAG) methods often struggle with complex biomedical queries that require accurate citation, iterative reasoning, and multi-step evidence synthesis. To address this challenge, we developed Queryome, a deep research system composed of specialized large language model (LLM) agents that dynamically adapt their orchestration to the complexity of each query. Queryome operates on a hybrid semantic-lexical retrieval engine covering 28.3 million PubMed abstracts and performs iterative, evidence-grounded synthesis through a hierarchical multi-agent architecture.Results
On the MIRAGE benchmark, Queryome achieved 89.93% accuracy, outperforming the best prior system by up to 9.96% points. On the biomedical subset of Humanity's Last Exam (HLE), it improved reasoning accuracy from 14.6% to 24.9% relative to the base reasoning model. In a review article construction task, Queryome achieved the highest composite score among deep research systems from OpenAI, Google, Perplexity, and Scite.ai, demonstrating strong capabilities in literature retrieval and synthesis.Conclusions
Queryome demonstrates that hierarchical, dynamically orchestrated multi-agent systems can substantially enhance evidence-based reasoning and synthesis over biomedical literature. Its consistent performance gains across diverse benchmarks suggest that agentic RAG architectures offer a promising path toward reliable, citation-grounded biomedical knowledge synthesis at scale.
Related
- Retrieval-to-abstraction LLM-assisted literature synthesis: Case demonstrations in digital health technology-enabled randomized controlled trial outcome reporting
- Teaching LLMs How ICU Physicians Approach Clinical Reasoning Through OMOP-Aligned Retrieval Improves Reasoning Across Clinical Domains
- Temporal-spatial reasoning over hypergraph knowledge structures for multimodal retrieval-augmented generation
- Intraoperative Breakage and Endoscopic Retrieval of a Dismantled Triprong Forceps During Ureterorenoscopic Lithotripsy: A Rare Complication and Review of the Literature
- Successful surgical retrieval of an intracranial sewing needle retained for more than 45 years since infancy with complete fibrous encapsulation: a case report and literature review.
BibTeX
@article{punuru2026queryome,
title = {{Queryome: orchestrating retrieval, reasoning, and synthesis across biomedical literature.}},
author = {Pranav Punuru and Nabil Ibtehaz and Swagarika Giri and Harsha Srirangam and Emilia Tugolukova and Daisuke Kihara},
journal = {Journal of biomedical semantics},
year = {2026},
month = aug,
doi = {10.1186/s13326-026-00366-5},
url = {https://europepmc.org/article/MED/43010075},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Queryome: orchestrating retrieval, reasoning, and synthesis across biomedical literature.
AU - Pranav Punuru
AU - Nabil Ibtehaz
AU - Swagarika Giri
AU - Harsha Srirangam
AU - Emilia Tugolukova
AU - Daisuke Kihara
PY - 2026
DA - 2026/08/12
JO - Journal of biomedical semantics
DO - 10.1186/s13326-026-00366-5
UR - https://europepmc.org/article/MED/43010075
AB - Background The rapid expansion of biomedical literature has made comprehensive manual synthesis increasingly difficult, creating a pressing need for AI systems capable of reasoning over verified evidence rather than merely retrieving it. Existing retrieval-augmented generation (RAG) methods often struggle with complex biomedical queries that require accurate citation, iterative reasoning, and multi-step evidence synthesis. To address this challenge, we developed Queryome, a deep research system composed of specialized large language model (LLM) agents that dynamically adapt their orchestration to the complexity of each query. Queryome operates on a hybrid semantic-lexical retrieval engine covering 28.3 million PubMed abstracts and performs iterative, evidence-grounded synthesis through a hierarchical multi-agent architecture.Results On the MIRAGE benchmark, Queryome achieved 89.93% accuracy, outperforming the best prior system by up to 9.96% points. On the biomedical subset of Humanity's Last Exam (HLE), it improved reasoning accuracy from 14.6% to 24.9% relative to the base reasoning model. In a review article construction task, Queryome achieved the highest composite score among deep research systems from OpenAI, Google, Perplexity, and Scite.ai, demonstrating strong capabilities in literature retrieval and synthesis.Conclusions Queryome demonstrates that hierarchical, dynamically orchestrated multi-agent systems can substantially enhance evidence-based reasoning and synthesis over biomedical literature. Its consistent performance gains across diverse benchmarks suggest that agentic RAG architectures offer a promising path toward reliable, citation-grounded biomedical knowledge synthesis at scale.
SN - 2041-1480
ER -