# MedAtlas: Evaluating LLMs for Multi-Round, Multi-Task Medical Reasoning Across Diverse Imaging Modalities and Clinical Text

arXiv: https://arxiv.org/abs/2508.10947 · HTML: https://mlsanity.com/paper/2508.10947/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 10 of its 29 references that are in the map.
- First posted on arXiv 13 Aug 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 10 of 10)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MIMIC-IT: Multi-Modal In-Context Instruction Tuning](https://mlsanity.com/paper/2306.05425/) (2023)
- [6G Wireless Communication Systems: Applications, Requirements, Technologies, Challenges, and Research Directions](https://mlsanity.com/paper/1909.11315/) (2019)
- [Lifting uniform learners via distributional decomposition](https://mlsanity.com/paper/2303.16208/) (2023)
- [Control of a Back-Support Exoskeleton to Assist Carrying Activities](https://mlsanity.com/paper/2305.06772/) (2023)
- [Maintenance cost assessment for heterogeneous multi-component systems incorporating perfect inspections and waiting time to maintenance](https://mlsanity.com/paper/2401.11538/) (2024)
- [Mixed Static and Reconfigurable Metasurface Deployment in Indoor Dense Spaces: How Much Reconfigurability is Needed?](https://mlsanity.com/paper/2402.00771/) (2024)

## Built on by (most cited first, 3 of 3)

- [IMCBench: A benchmark for multimodal LLMs in Image-grounded Medical Conversations](https://mlsanity.com/paper/2606.28556/) (2026)
- [Evaluating the Diagnostic Robustness of Vision-Language Models Under Visual and Textual Perturbations](https://mlsanity.com/paper/2608.04885/) (2026)
- [How Good are Foundation Models in Longitudinal MRI Disease Progression Reasoning?](https://mlsanity.com/paper/2608.13309/) (2026)

## Abstract (arXiv)

Artificial intelligence has demonstrated significant potential in clinical decision-making; however, developing models capable of adapting to diverse real-world scenarios and performing complex diagnostic reasoning remains a major challenge. Existing medical multi-modal benchmarks are typically limited to single-image, single-turn tasks, lacking multi-modal medical image integration and failing to capture the longitudinal and multi-modal interactive nature inherent to clinical practice. To address this gap, we introduce MedAtlas, a novel benchmark framework designed to evaluate large language models on realistic medical reasoning tasks. MedAtlas is characterized by four key features: multi-turn dialogue, multi-modal medical image interaction, multi-task integration, and high clinical fidelity. It supports four core tasks: open-ended multi-turn question answering, closed-ended multi-turn question answering, multi-image joint reasoning, and comprehensive disease diagnosis. Each case is derived from real diagnostic workflows and incorporates temporal interactions between textual medical histories and multiple imaging modalities, including CT, MRI, PET, ultrasound, and X-ray, requiring models to perform deep integrative reasoning across images and clinical texts. MedAtlas provides expert-annotated gold standards for all tasks. Furthermore, we propose two novel evaluation metrics: Round Chain Accuracy and Error Propagation Resistance. Benchmark results with existing multi-modal models reveal substantial performance gaps in multi-stage clinical reasoning. MedAtlas establishes a challenging evaluation platform to advance the development of robust and trustworthy medical AI.