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

arXiv: https://arxiv.org/abs/2505.18283 · HTML: https://mlsanity.com/paper/2505.18283/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 22 of its 44 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- Retrieval-augmented generation / [Medical and biomedical RAG](https://mlsanity.com/rag/medical-and-biomedical-rag/)

## Builds on (most cited first, 22 of 22)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning](https://mlsanity.com/paper/2311.10537/) (2023)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding](https://mlsanity.com/paper/2501.18362/) (2025)
- [MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making](https://mlsanity.com/paper/2404.15155/) (2024)
- [A Survey of Large Language Models in Medicine: Progress, Application, and Challenge](https://mlsanity.com/paper/2311.05112/) (2023)
- [MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs](https://mlsanity.com/paper/2504.00993/) (2025)
- [Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions](https://mlsanity.com/paper/2402.18060/) (2024)
- [Benchmarking large language models for biomedical natural language processing applications and recommendations](https://mlsanity.com/paper/2305.16326/) (2023)
- [MedExQA: Medical Question Answering Benchmark with Multiple Explanations](https://mlsanity.com/paper/2406.06331/) (2024)
- [MedCoT: Medical Chain of Thought via Hierarchical Expert](https://mlsanity.com/paper/2412.13736/) (2024)
- [MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks](https://mlsanity.com/paper/2503.07459/) (2025)
- [MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning](https://mlsanity.com/paper/2405.03000/) (2024)
- [MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation](https://mlsanity.com/paper/2503.13856/) (2025)
- [Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical Scenarios](https://mlsanity.com/paper/2411.14461/) (2024)

## Built on by (most cited first, 2 of 2)

- [Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning](https://mlsanity.com/paper/2607.07761/) (2026)
- [From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning](https://mlsanity.com/paper/2604.06262/) (2026)

## Abstract (arXiv)

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 domain-specific 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. The code will be available at https://github.com/JianghaoWu/TAGS.