Multi-Agent Medical Evidence & Triage System
A task-oriented medical AI agent system for health consultation, risk triage and evidence-based research, combining multi-agent orchestration, hybrid retrieval, dual-layer memory and safety constraints.
About
I am Zhiwei Lai (赖至伟), a Master of Bioinformatics graduate from the University of Melbourne with an undergraduate background in Pharmacy from Peking University.
My current interests lie at the intersection of large language models and biomedical AI, with a focus on AI agents, retrieval-augmented generation, agentic post-training, multimodal systems, and AI for science. I am particularly interested in building reliable LLM systems for medical reasoning, evidence search, and biological sequence modeling.
Education
-
2023 – 2025
University of Melbourne
Master of Bioinformatics · Melbourne, Australia
Graduate with Distinction · Dean's List -
2018 – 2023
Peking University
B.S. in Pharmacy · Beijing, China
Selected Projects
Medical Deep Search Agent with Agentic Post-training
A medical Deep Search agent post-training project focused on long-horizon tool use, evidence acquisition, recovery behavior and agent policy optimization through Agentic SFT, Recovery SFT and Agentic RL.
Protein Language Models for Antimicrobial Peptide Discovery
A computational antimicrobial peptide discovery project organized around a Generate → Filter → Rank framework, covering conditional peptide generation, AMP/non-AMP classification and MIC activity ranking with protein language models and graph-based representations.
Technical Writing
Contact
Email: zhiwei.lai@pku.edu.cn
GitHub: EdwardLaiPKU