bowang-lab/MedRAX
MedRAX is a versatile AI agent that integrates advanced chest X-ray analysis tools and multimodal large language models to provide comprehensive medical reasoning and interpretation for complex clinical queries.
Awesome AI Agents › Medical & Healthcare
AQ-MedAI/MedResearcher-R1
MedResearcher-R1 is both a released 32B reasoning model for medical deep research and the open framework used to produce its training data. The framework has three linked stages. The first builds a domain knowledge graph and synthesises questions from it: five subgraph sampling strategies, including augmented chains, community core paths and dual core bridges, extract complex structures from the graph, and a generation step turns each structure into a multi-hop question with deliberate concept obfuscation, a verified answer and a step-by-step reasoning cheat sheet. An interactive web interface visualises the graph with D3 force layouts, and batch generation runs concurrently with rate control, progress monitoring and resume. The second stage converts those question-answer pairs into full agent trajectories: a multi-turn agent framework solves each question with tool calls, then quality filters check token budgets and that every tool call has a matching response, and a rewriting step called Masked Trajectory Guidance uses an LLM to repair and tighten trajectories before they become training data. The third stage evaluates models, either one question at a time with the reasoning steps shown, or in parallel batch runs across benchmarks with configurable rollouts and timeouts. The authors report results on MedBrowseComp, GAIA and XBench-DeepSearch, and publish both the model on Hugging Face and a sample of the generated question set in the repository. The paper is on arXiv and the documentation is available in English and Chinese. The intended users are researchers and teams training domain specialised research agents: the medical setting is the demonstration, while the graph-to-trajectory pipeline is meant to transfer to other fields where reliable multi-hop reasoning data is scarce.
https://github.com/AQ-MedAI/MedResearcher-R1
Also in Medical & Healthcare
souvikmajumder26/Multi-Agent-Medical-Assistant
Multi-Agent Medical Assistant is an AI-powered chatbot system that integrates multi-agent orchestration, advanced retrieval-augmented generation, and medical image analysis to assist healthcare professionals, researchers, and patients with medical diagnosis and healthcare research.
mims-harvard/TxAgent
TxAgent is an AI agent that leverages multi-step reasoning and a comprehensive toolbox of biomedical tools to provide personalized and precise therapeutic treatment recommendations based on real-time biomedical knowledge and clinical guidelines.
gersteinlab/MedAgents
MedAgents is a Multi-disciplinary Collaboration framework leveraging large language models to facilitate zero-shot medical reasoning through expert gathering, iterative analysis, and consensus-driven decision making.
mingze-yuan/Awesome-LLM-Healthcare
A curated repository of research papers and resources reviewing the transformative applications and challenges of Large Language Models in medicine and healthcare.