TAGS: A Test-Time Generalist–Specialist Framework with Retrieval-Augmented Reasoning and Verification

Recent advances such as Chain-of-Thought prompting have significantly improved large language models (LLMs) in zero-shot medical reasoning.However, prompting-based methods often remain shallow and unstable, while fine-tuned medical LLMs suffer from poor generalization under distribution shifts and limited adaptability to unseen clinical scenarios.To address these limitations, we present TAGS, a test-time framework that combines a broadly capable generalist with a domainspecific specialist to offer complementary perspectives without any model fine-tuning or parameter updates.To support this generalist-specialist reasoning process, we introduce two auxiliary modules: a hierarchical retrieval mechanism that provides multi-scale exemplars by selecting examples based on both semantic and rationale-level similarity, and a reliability scorer that evaluates reasoning consistency to guide final answer aggregation.TAGS achieves strong performance across nine MedQA benchmarks, boosting GPT-4o accuracy by 13.8%, DeepSeek-R1 by 16.8%, and improving a vanilla 7B model from 14.1% to 23.9%.These results surpass several fine-tuned medical LLMs, without any parameter updates.Outside Training Data Question: Child with Type I Diabetes.What is the advised time for fundus examinations from the time of diagnosis?Options: A. After 5 years B. After 2 years C.After 10 years D. At the time of diagnosis Reasoning Process: Diabetic retinopathy is a complication of diabetes that affects the eyes.It is caused by damage to the blood vessels of the light-sensitive tissue at the back of the eye (retina)…