A large-scale clinical trial corpus and benchmark for building and evaluating specialized AI systems.
Zifeng Wang
I develop language models and AI agents for reasoning, tool use, and autonomous scientific discovery. My work combines SFT, RLVR, and agentic reinforcement learning with executable research environments and scalable agent systems. My papers have been cited 4,500+ times with an h-index of 30+.
I received my Ph.D. in Computer Science from UIUC. Previously, I co-founded Keiji.AI and led a team of 10+ researchers and engineers, building AI co-scientists deployed at 10+ biopharma organizations.
Selected work
All publications ↗Scientific reasoning across biomedical knowledge graphs and evidence chains.
Code-generating agents with executable feedback for biomedical data analysis.
A specialized model for human–AI collaboration in medical literature review.
Using language models to support systematic clinical evidence synthesis.
Matching patients to clinical trials with interpretable language-model reasoning.
Experience
Background ↗2025–2026
Co-founder & Chief AI Scientist · Keiji.AI
Led research and engineering across scientific agents, evaluation, and production deployment, translating research into tools for clinical development.
Recent updates
- Jul 2026Our tutorial on LLMs for medical research was accepted in Nature Protocols.
- Jun 2026New work on clinical reasoning, deep evidence research, and data science agents.