Hao Zhang

Research Scientist at ByteDance

Context infrastructure for agents.

Shared information environments for multi-agent and human–agent collaboration.

I am a Research Scientist at ByteDance. I build self-improving context infrastructure toward a future where AI agents collaborate with one another and with humans.

My focus is the shared, evolving information environments behind this collaboration: how knowledge, memory, and work artifacts are organized, maintained, and turned into the right context for each participant and task. The goal is to let people and agents build on one another’s work over time, while keeping track of changing information and human decisions.

Current Focus

My current research studies how to organize heterogeneous information into reusable representations and access paths, and improve them through task-level feedback. The longer-term goal is sustained collaboration among humans and multiple agents: a shared information environment, with the right context for each participant.

At ByteDance, I develop AutoIA, focusing on how task-level feedback can improve retrieval pipelines and the underlying information environments.

My Independent Research spans separate projects and academic collaborations across data systems and AI, including semantic query processing, document retrieval, and hardware-efficient graph algorithms.

Longer-term view

Selected Projects

Independent Research — research projects and academic collaborations across data systems and AI.
AutoIA @ ByteDance — self-improving context infrastructure.
GES @ Huawei — production graph database infrastructure.
TQEX @ Huawei — tensor-centric SQL and graph execution on heterogeneous accelerators.
Database & Graph Research Systems @ CUHK — distributed query processing and graph systems.

Publications contains the full research record.

Highlights

30+ publications in database systems and AI, including SIGMOD, VLDB, ICDE, EMNLP, COLM, TKDE, and The VLDB Journal.
#1 on both tracks of LDBC SNB Interactive, the leading audited benchmark for graph database systems: Declarative, 2024 (3,000× over #2) and Imperative, 2025.

I received my Ph.D. from the Chinese University of Hong Kong, advised by Prof. Jeffrey Xu Yu and Prof. Hong Cheng, and my B.S. in Computer Science from Wuhan University.

Selected Honors & Awards

ByteDance Soaring Star Talent Program
Huawei Gold Award for Individual Excellence — Top 1%
Huawei TopMinds Talent Program — First Class (highest tier)

Collaboration & Internship

I welcome collaboration on context infrastructure, retrieval systems, and graph/vector systems. I am also recruiting research interns at ByteDance in Shenzhen; email zhanghaowuda12 [at] gmail [dot] com with [Intern] in the subject.