STORM & Co‑STORM — 2024
Human and multi-agent co‑curate sources and synthesize long citation‑grounded reports.
- 800k users for research and writing workflows.
- Human‑in‑the‑loop moderation; agents surface perspectives and evidence.
Yucheng Jiang
Human–AI interaction and collaboration
I am a first-year PhD student in Computer Science at Stanford University, working at the intersection of NLP and HCI. I develop human-centered AI systems in which language-model agents collaborate with people to curate knowledge, solve complex problems, and produce grounded, actionable artifacts. I completed my M.S. in Computer Science at Stanford and my B.S. at the University of Illinois Urbana-Champaign.
If you'd like to chat, feel free to book a time or email me.
Currently, I'm interested in the following questions:
- How can NLP systems reliably augment human expertise and decision-making?
- How should LLM agents handle long-horizon tasks with persistent memory and experience?
- How can LLM agents learn from collaborating with humans?
Selected Projects
Recent Publications
Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations
Future of Work with AI Agents: Auditing Automation and Augmentation Potential across the U.S. Workforce
Unmasking True Clinical Competence: The Importance of Adaptive and Open-Ended Evaluation for Large Language Models in Cardiology
Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration
Experience
Stanford University
Ph.D. Student, Computer Science
Jun. 2025 – Present
Stanford University
Master of Science in Computer Science
Sep. 2023 – Mar. 2025
Apple
Software Development Engineer
Jan. 2023 – Sep. 2023
Apple
Software Engineer Intern
May 2022 – Aug. 2022
University of Illinois Urbana‑Champaign
Aug. 2019 – Dec. 2022