About Me
Haoxiang Zhang 张灏翔
Intelligence is born of bounded stochasticity.
Hello! 好呀 ~ こんちは!
Hello! I am a passionate data researcher focusing on data centric AI. I am currently pursuing my Master of Science in Data Science at UC San Diego. I now work closely with Prof. Julian McAuley's lab @ UCSD and Prof. Yu Zhang's lab @ Texas A&M University. Previously, I was a visiting student @ Stanford University, working with Dr. Pan Lu, where I was fortunate to be advised by Prof. Yejin Choi and Prof. James Zou.
My research experienced computer vision, continual learning, out-of-distribution generalization, and agentic LLMs. Right now I'm exploring training efficiency and balance between agent benchmaxxing and human interaction. Looking forward to discussing new inspirations!
Selected Publications
Masking Stale Observations Helps Search Agents – Until It Doesn't: A Regime Map and Its Mechanism
Haoxiang Zhang*Equal contribution, Qixin Xu*Equal contribution, Yu Zhang✝Co-senior author, Julian McAuley✝Co-senior author, and 3 more authors
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
Zhuofeng Li, Haoxiang Zhang, Dongfu Jiang✝Corresponding author, Yu Zhang✝Corresponding author, and 15 more authors
Eubiota: Modular Agentic AI for Autonomous Discovery in the Gut Microbiome
Pan Lu*Equal contribution, Yifan Gao*Equal contribution, Haoxiang Zhang, and 12 more authors
In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
Zhuofeng Li*Equal contribution, Haoxiang Zhang*Equal contribution, James Zou✝Corresponding author, Pan Lu✝Corresponding author, and 5 more authors
GitHub ⭐
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Zhuofeng Li*Equal contribution, Dongfu Jiang*Equal contribution, Xueguang Ma, Haoxiang Zhang, and 6 more authors
GitHub ⭐
Avoiding Structural Pitfalls: Self-Supervised Low-Rank Feature Tuning for Graph Test-Time Adaptation
Haoxiang Zhang, Zhuofeng Li, Shichao Pei✝Corresponding author, and 3 more authors
Programme Committee Service
Reviewer: ARR 2026 | EMNLP 2026 | NIPS 2026 | ICLR 2026 | COLM 2026 WAB | COLM 2026 LLA
Long-term Collaboration
Education
Wharton Innovation, Entrepreneurship and Leadership Program & The Global Leadership Program for Young Scholars.
07/2023 - 08/2023
Industrial Internship
Salesforce AI Research, Palo Alto
Agent Self Evolution
06/2026 - 09/2026
Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight
Haoxiang Zhang, Qinglin Chen, Hiroaki Hayashi, and 9 more authors
Shanghai Artificial Intelligence Labotary
Multimodal Unified Auto-regressive Generation.
View Detail [Lumina-mGPT]08/2024 - 02/2025