I am Qi Zhang (张棋), also called Max — an Applied Scientist at AWS Security Analytics and AI Research (SAAR), and hold a Ph.D. in Computer & Information Sciences from Temple University, where I was advised by Eduard Dragut and worked closely with Cornelia Caragea and Longin Jan Latecki.

My research is in LLM agents, AI security, LLMs, NLP, and machine learning. I am always glad to talk about any of it — write to me.

Research

• 01
  LLM Agents

  Agent systems that use tools, reason across many steps, and recover from their own mistakes.
• 02
  AI Agent Security

  Tool-use security, robustness, and anomaly detection for agents that act in the real world.
• 03
  LLMs → Structured Knowledge

  Extracting entities, relations, and complex structure from scientific and domain-specific text.
• 04
  Structured Knowledge → LLMs

  Using knowledge graphs and taxonomies to improve reasoning, factuality, and adaptability.

News

• 2026.04Successfully defended my Ph.D. dissertation. I am Dr. Zhang now.
• 2026.04Four papers accepted to ACL 2026 — see you in San Diego.
• 2026.03Started as Applied Scientist at AWS GuardDuty.
• 2025.09Started as Applied Scientist Intern at AWS, working with Qian Cui and Zhilu Zhang.
• 2025.05Summer research intern at Intuit AI Research, working with Xiang Gao and Yuguang Yao.
• 2025.04One paper accepted to ACL 2025.
• 2025.01One paper accepted to NAACL 2025 — see you in Albuquerque.

Selected Publications

• Scaling Performance and Low-Resource Annotation with Many-Shot In-Context Learning for Named Entity Recognition Qi Zhang, Fangping Lan, Cornelia Caragea, Longin Jan Latecki, Eduard Dragut ACL 2026 · Findings
• RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning Xiang Gao, Yuguang Yao, Qi Zhang, Kun Dong, Avirup Baidya, Rui Guo, Hugo Hasson, Kanak Das ACL 2026 · Main
• Metacognitive Self-Correction for Multi-Agent Systems via Prototype-Guided Next-Execution Reconstruction Qi Zhang, Xu Shen, Song Wang, Zhen Tan, Xinyu Zhao, Laura Yao, Vaishnav Tadiparthi, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Kwonjoon Lee, Tianlong Chen ACL 2026 · Findings
• DynClean: Training Dynamics-based Label Cleaning for Distantly-Supervised Named Entity Recognition Qi Zhang, Huitong Pan, Zhijia Chen, Longin Jan Latecki, Cornelia Caragea, Eduard Dragut NAACL 2025 · Findings
• SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents Qi Zhang, Zhijia Chen, Huitong Pan, Cornelia Caragea, Longin Jan Latecki, Eduard Dragut EMNLP 2024 · Main (20.8% acceptance)
• DMDD: A Large-Scale Dataset for Dataset Mention Detection Huitong Pan, Qi Zhang, Eduard Dragut, Cornelia Caragea, Longin Jan Latecki TACL

All publications →

Writing

• August 19, 2026 Writing Things Down
  Why I am keeping notes in public, and what I expect to put here.

All notes →