Zihao Zhang 张子昊
About Me
I am a PhD student in the Department of Computer Science at Emory University, fortunate to be advised by Prof. Li Xiong. Previously, I was fortunate to be advised by Dr. Fei Liu. Before Emory, I received my M.S. in Computer Science from UMass Amherst, advised by Prof. Hong Yu, and my B.S. in Computer Science (Honors Program) from Penn State University, with minors in Mathematics, Statistics, and Cybersecurity.
Research Interests: My primary research interests include large language models, LLM agents. Specifically, my current research focuses on:
- LLM Safety & Privacy: privacy risks and safeguards for LLMs and agentic systems, and building trustworthy agents that act safely on users' behalf.
- LLM Agents and Planning: how agents plan under cost constraints, tree-search planning, and evaluating the planning capabilities of LLMs.
- Coding Agents: harness design, context management, and training for long-horizon software-engineering agents.
I am happy to collaborate and/or answer questions about my research. If you are interested in research collaboration or have any inquiries about my experience, please send me an email.
I am currently seeking research internship opportunities for Summer 2027. Feel free to reach out!
News
- 2026.09New preprint: An Empirical Study of Harness Design for Coding Agents.
- 2026.05Started as a GenAI Research Intern at Zoom in Bellevue, WA, working on agentic personalized meeting summarization and coding-agent harness.
- 2026.01Our paper MedQA-CS is accepted as EACL 2026 Oral.
- 2025.05Our paper PlanGenLLMs received the Senior Area Chair Highlights Award at ACL 2025 (top 1% of 8,000+ submissions).
- 2025.05New preprint: Cost-Awareness in Tree-Search LLM Planning: A Systematic Study.
- 2024.10New preprint: MedQA-CS, an OSCE-style benchmark for evaluating the clinical skills of LLMs.
- 2024.08Started my PhD in Computer Science at Emory University.
- 2023.12Completed my M.S. in Computer Science at UMass Amherst.
- 2023.12Our paper EHRTutor was accepted to the NeurIPS 2023 Workshop on Generative AI for Education (GAIED).
Publications
* indicates equal contribution
Internship Experience
- 2026.05 – 2026.08Zoom Communications, Inc.GenAI Research Intern, Bellevue, WA
- Independently designed and built Zoom's next-generation agentic personalized meeting summarization end-to-end, under the guidance of my mentors.
- Evaluate harness components on SWE-bench and Terminal-Bench, diagnosing coding-agent failures and behavior through trajectory- and command-level error analyses.
Education
- 2024 – PresentEmory UniversityDepartment of Computer SciencePh.D. in Computer Science, advised by Dr. Li Xiong; previously advised by Dr. Fei Liu.
- 2021 – 2023University of Massachusetts AmherstManning College of Information & Computer SciencesM.S. in Computer Science, advised by Dr. Hong Yu.
- 2017 – 2021The Pennsylvania State UniversityB.S. in Computer Science (Honors Program)Minors in Mathematics, Statistics, and Cybersecurity
Honors & Awards
- 2025Senior Area Chair Highlights Award, ACL 2025 (top 1% of 8,000+ submissions), for PlanGenLLMs
Academic Service
- Area ChairEMNLP · ARR
- ReviewerICLR
Teaching
- Spring & Fall 2025CS 526: AlgorithmsTeaching Assistant · Emory University
- Fall 2024CS 571: Natural Language ProcessingTeaching Assistant · Emory University