Agentic large language models improve retrieval-based radiology question answering

• URL: http://arxiv.org/abs/2508.00743v1
• Date: Fri, 01 Aug 2025 16:18:52 GMT
• Title: Agentic large language models improve retrieval-based radiology question answering
• Authors: Sebastian Wind, Jeta Sopa, Daniel Truhn, Mahshad Lotfinia, Tri-Thien Nguyen, Keno Bressem, Lisa Adams, Mirabela Rusu, Harald Köstler, Gerhard Wellein, Andreas Maier, Soroosh Tayebi Arasteh,
• Abstract summary: Agentic retrieval significantly improved mean diagnostic accuracy over zero-shot prompting.<n>The greatest gains occurred in midsized models.<n>Even clinically fine-tuned models exhibited meaningful improvements.
• Score: 4.340742745938289
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Clinical decision-making in radiology increasingly benefits from artificial intelligence (AI), particularly through large language models (LLMs). However, traditional retrieval-augmented generation (RAG) systems for radiology question answering (QA) typically rely on single-step retrieval, limiting their ability to handle complex clinical reasoning tasks. Here we propose an agentic RAG framework enabling LLMs to autonomously decompose radiology questions, iteratively retrieve targeted clinical evidence from Radiopaedia, and dynamically synthesize evidence-based responses. We evaluated 24 LLMs spanning diverse architectures, parameter scales (0.5B to >670B), and training paradigms (general-purpose, reasoning-optimized, clinically fine-tuned), using 104 expert-curated radiology questions from previously established RSNA-RadioQA and ExtendedQA datasets. Agentic retrieval significantly improved mean diagnostic accuracy over zero-shot prompting (73% vs. 64%; P<0.001) and conventional online RAG (73% vs. 68%; P<0.001). The greatest gains occurred in mid-sized models (e.g., Mistral Large improved from 72% to 81%) and small-scale models (e.g., Qwen 2.5-7B improved from 55% to 71%), while very large models (>200B parameters) demonstrated minimal changes (<2% improvement). Additionally, agentic retrieval reduced hallucinations (mean 9.4%) and retrieved clinically relevant context in 46% of cases, substantially aiding factual grounding. Even clinically fine-tuned models exhibited meaningful improvements (e.g., MedGemma-27B improved from 71% to 81%), indicating complementary roles of retrieval and fine-tuning. These results highlight the potential of agentic frameworks to enhance factuality and diagnostic accuracy in radiology QA, particularly among mid-sized LLMs, warranting future studies to validate their clinical utility.

Related papers

• Handcrafted vs. Deep Radiomics vs. Fusion vs. Deep Learning: A Comprehensive Review of Machine Learning -Based Cancer Outcome Prediction in PET and SPECT Imaging [0.7573820776203027]
  This systematic review analyzed 226 studies published from 2020 to 2025 that applied machine learning to PET or SPECT imaging for outcome prediction.<n> PET-based studies generally outperformed those using SPECT, likely due to higher spatial resolution and sensitivity.<n>Common limitations included inadequate handling of class imbalance, missing data, and low population diversity.
  arXiv  Detail & Related papers  (2025-07-21T21:03:12Z)
• An Agentic System for Rare Disease Diagnosis with Traceable Reasoning [58.78045864541539]
  We introduce DeepRare, the first rare disease diagnosis agentic system powered by a large language model (LLM)<n>DeepRare generates ranked diagnostic hypotheses for rare diseases, each accompanied by a transparent chain of reasoning.<n>The system demonstrates exceptional diagnostic performance among 2,919 diseases, achieving 100% accuracy for 1013 diseases.
  arXiv  Detail & Related papers  (2025-06-25T13:42:26Z)
• ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification [57.22053411719822]
  ChestX-Reasoner is a radiology diagnosis MLLM designed to leverage process supervision mined directly from clinical reports.<n>Our two-stage training framework combines supervised fine-tuning and reinforcement learning guided by process rewards to better align model reasoning with clinical standards.
  arXiv  Detail & Related papers  (2025-04-29T16:48:23Z)
• How Well Can Modern LLMs Act as Agent Cores in Radiology Environments? [54.36730060680139]
  RadA-BenchPlat is an evaluation platform that benchmarks the performance of large language models (LLMs) in radiology environments.<n>The platform also defines ten categories of tools for agent-driven task solving and evaluates seven leading LLMs.
  arXiv  Detail & Related papers  (2024-12-12T18:20:16Z)
• AI-assisted prostate cancer detection and localisation on biparametric MR by classifying radiologist-positives [5.75804178993065]
  We propose to develop deep learning models that improve the overall cancer diagnostic accuracy. We develop a single voxel-level classification model, with a simple percentage threshold to determine positive cases. Based on the presented experiments from two clinical data sets, we show that the proposed strategy can improve the diagnostic accuracy.
  arXiv  Detail & Related papers  (2024-10-30T14:59:57Z)
• MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models [49.765466293296186]
  Recent progress in Medical Large Vision-Language Models (Med-LVLMs) has opened up new possibilities for interactive diagnostic tools.<n>Med-LVLMs often suffer from factual hallucination, which can lead to incorrect diagnoses.<n>We propose a versatile multimodal RAG system, MMed-RAG, designed to enhance the factuality of Med-LVLMs.
  arXiv  Detail & Related papers  (2024-10-16T23:03:27Z)
• MGH Radiology Llama: A Llama 3 70B Model for Radiology [50.42811030970618]
  This paper presents an advanced radiology-focused large language model: MGH Radiology Llama.<n>It is developed using the Llama 3 70B model, building upon previous domain-specific models like Radiology-GPT and Radiology-Llama2.<n>Our evaluation, incorporating both traditional metrics and a GPT-4-based assessment, highlights the enhanced performance of this work over general-purpose LLMs.
  arXiv  Detail & Related papers  (2024-08-13T01:30:03Z)
• RadioRAG: Online Retrieval-augmented Generation for Radiology Question Answering [1.7618750189510493]
  Large language models (LLMs) often generate outdated or inaccurate information based on static training datasets.<n>Retrieval-augmented generation (RAG) mitigates this by integrating outside data sources.<n>We have developed Radiology RAG (RadioRAG), an end-to-end framework that retrieves data from authoritative radiologic online sources in real-time.
  arXiv  Detail & Related papers  (2024-07-22T13:29:56Z)
• ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data [115.0747462486285]
  ChatRadio-Valuer is a tailored model for automatic radiology report generation that learns generalizable representations. The clinical dataset utilized in this study encompasses a remarkable total of textbf332,673 observations. ChatRadio-Valuer consistently outperforms state-of-the-art models, especially ChatGPT (GPT-3.5-Turbo) and GPT-4 et al.
  arXiv  Detail & Related papers  (2023-10-08T17:23:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.