paper-with-me

홈 › Papers

MedCTA: A Benchmark for Clinical Tool Agents

2026-06-10 · Tajamul Ashraf, Hyewon Jeong, Fida Mohammad Thoker, Bernard Ghanem arxiv

To make clinically grounded decisions, medical AI agents are expected to go beyond simple recognition and be capable of tool retrieval, evidence acquisition, and integration. Existing benchmarks largely evaluate isolated perception or single-turn question answering, and therefore provide limited visibility into failures of planning, tool recruitment, and rollout reliability. We introduce MedCTA, a benchmark for evaluating medical tool agents on clinician-validated, step-implicit tasks grounded in realistic multimodal clinical inputs, including radiology images, pathology slides, and reports. MedCTA comprises 107 real-world clinical tasks with clinician-verified executable trajectories over 5 deployed tools, and supports process-aware evaluation of tool selection, argument validity, execution stability, trajectory fidelity, and outcome quality. We benchmark 18 open- and closed-source multimodal models and find that even frontier systems remain brittle in multi-step clinical tool use: autonomous rollouts are dominated by protocol failures, premature stopping, and incorrect tool recruitment, while gold-standard tool routing yields large but still incomplete gains. These results show that strong backbone perception does not translate into reliable agentic behavior in clinical settings. MedCTA provides a rigorous testbed for auditing, diagnosing, and advancing trustworthy medical AI agents. The dataset and evaluation suite are available at https://ivul-kaust.github.io/MedCTA/

📄 PDF Abstract BibTeX arXiv:2606.11702

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

ReflecTool: Towards Reflection-Aware Tool-Augmented Clinical Agents

2024-10-23 · Yusheng Liao, Shuyang Jiang, Yanfeng Wang, Yu Wang

Large Language Models (LLMs) have shown promising potential in the medical domain, assisting with tasks like clinical note generation and patient communication. However, current LLMs are limited to text-based communicati…

CodeClinic: Evaluating Automation of Coding Skills for Clinical Reasoning Agents

2026-05-10 · Timothy Ossowski, Xinchi Liu, Danyal Maqbool, Vaibhav Dhanuka 외 arxiv

Clinical reasoning agents based on large language models (LLMs) aim to automate tasks such as intensive care unit (ICU) monitoring and patient state tracking from electronic health records (EHRs). Existing systems typica…

Code Generation

AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments

2024-05-13 · Samuel Schmidgall, Rojin Ziaei, Carl Harris, Eduardo Reis 외

Evaluating large language models (LLM) in clinical scenarios is crucial to assessing their potential clinical utility. Existing benchmarks rely heavily on static question-answering, which does not accurately depict the c…

Decision MakingDiagnosticMedQAQuestion Answering+1

Agentic AI in medicine: architectures, applications, evaluation, and challenges for clinical translation

2026-07-28 · Zheng Tong, Yang Liu, Wanshu Fan, Jing Qin 외 arxiv

Large language models and multimodal foundation models are enabling medical artificial intelligence (AI) systems to move beyond isolated prediction and undertake multistep clinical tasks that require planning, tool use, …

Question Answering

DeepTumorVQA: A Hierarchical 3D CT Benchmark for Stage-Wise Evaluation of Medical VLMs and Tool-Augmented Agents

2026-05-10 · Yixiong Chen, Wenjie Xiao, Pedro R. A. S. Bassi, Boyan Wang 외 arxiv

Medical vision-language models (VLMs) and AI agents have made significant progress in learning to analyze and reason about clinical images. However, existing medical visual question answering (VQA) benchmarks collapse mo…

Visual Question AnsweringVisual Reasoning