I am a Ph.D. student in Computer Science at the University of Illinois Chicago, advised by Professor Philip S. Yu in the BDSC lab. Expected graduation: May 2028.

My research focuses on agent memory, interactive evaluation, deep research, and human–agent collaboration. I am currently an Applied Scientist Intern at Amazon Quick, building multi-agent software generation systems for sandbox environment creation.

Download my CV (PDF)

🔬 Research Interests

• Agentic Memory & Lifelong Personalization: Memory and retrieval for long-horizon agents, self-evolving skills, and lifelong personalization. Related work: Harness the Memory, Memory Survey, MemoryCD, MemAudit, HyperSkill
• Agent Evaluation & Interactive Benchmarking: Benchmarks for long-horizon tasks, human participation, interruption, and mid-task steering. Related work: JARVIS-Bench, HAS-Bench, InterruptBench, RECODE-H
• Agentic Deep Research, Tool Use & RL: Search and reasoning agents, agentic RAG, reinforcement learning, and multi-stage safety guardrails. Related work: DeepResearchGuard, Deep Research Survey, RAG Survey, CoEvoSkills, Data Synthesis Survey, Action Bottleneck
• Human–Agent Collaboration & Trustworthy Systems: Human feedback, multi-agent debate and coordination, and trustworthy, personality-aware interaction. Related work: MADIAVE, Human–Agent Survey, Autonomous Driving Survey, Collaborative Intelligence, PSG-Agent, RECODE-H, XBridge

🔥 News

📝 Selected Publications

Selected papers from my research. View all publications ↓ · * Equal contribution.

NeurIPS 2026 (ED Track)

Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents

Wei-Chieh Huang, Weizhi Zhang, Yuchen Wu, Yankai Chen, …, Philip S. Yu, Xue Liu, Aylin Caliskan

Paper · Citation details

TMLR 2026

A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents

Authors · including Wei-Chieh Huang

Wei-Chieh Huang^*, Weizhi Zhang^*, Yueqing Liang^*, Yuanchen Bei, Yankai Chen, Tao Feng, Xinyu Pan, Zhen Tan, Yu Wang, Tianxin Wei, …, Jiawei Han, Philip S. Yu, Kai Shu

🏆 Survey Certification

ACL 2026 Main

Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety

Authors · including Wei-Chieh Huang

Wei-Chieh Huang, Henry Peng Zou, Yaozu Wu, Dongyuan Li, Yankai Chen, Weizhi Zhang, Yangning Li, Angelo Zangari, Jizhou Guo, Chunyu Miao, Liancheng Fang, Langzhou He, Yinghui Li, Renhe Jiang, Philip S. Yu

EACL 2026 Findings

MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction

Wei-Chieh Huang, Cornelia Caragea

ACL 2026 Findings

LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey

Authors · including Wei-Chieh Huang

Henry Peng Zou^*, Wei-Chieh Huang^*, Yaozu Wu^*, Jizhou Guo, Yankai Chen, Chunyu Miao, Hoang Nguyen, Yue Zhou, Weizhi Zhang, Liancheng Fang, Hanrong Zhang, Fangxin Wang, Pengfei Zhang, Huacan Wang, Langzhou He, Yangning Li, Dongyuan Li, Renhe Jiang, Xue Liu, Philip S. Yu

Under Review, 2026

A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy

Authors · including Wei-Chieh Huang

Henry Peng Zou^*, Wei-Chieh Huang^*, Yaozu Wu^*, Chunyu Miao, Dongyuan Li, Aiwei Liu, Yue Zhou, Yankai Chen, Weizhi Zhang, Yangning Li, Liancheng Fang, Renhe Jiang, Philip S. Yu

EMNLP 2025

Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs

Authors · including Wei-Chieh Huang

Yangning Li^*, Weizhi Zhang^*, Yuyao Yang, Wei-Chieh Huang, Yaozu Wu, Junyu Luo, Yuanchen Bei, Henry Peng Zou, Xiao Luo, Yusheng Zhao, Chunkit Chan, Yankai Chen, Zhongfen Deng, Yinghui Li, Hai-Tao Zheng, Dongyuan Li, Renhe Jiang, Ming Zhang, Yangqiu Song, Philip S. Yu

Under Review, 2026

From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents

Authors · including Wei-Chieh Huang

Weizhi Zhang^*, Yangning Li^*, Wei-Chieh Huang^*, Yuanchen Bei, Junyu Luo, Guancheng Wan, Liangwei Yang, Chenxuan Xie, Yuyao Yang, Chunyu Miao, Henry Peng Zou, Xiao Luo, Yusheng Zhao, Yankai Chen, Chunkit Chan, Peilin Zhou, Xinyang Zhang, Chenwei Zhang, Jingbo Shang, Ming Zhang, Yangqiu Song, Irwin King, Philip S. Yu

📚 All Publications

See also my Google Scholar profile. * Equal contribution.

📖 Education

• 2024.08–Present, Ph.D. in Computer Science, University of Illinois Chicago (UIC), US. Expected graduation: May 2028.
• 2020.09 - 2022.12, M.S. in Systems Engineering, Cornell University, US.
• 2013.09 - 2017.06, B.S. in Chemical Engineering, National Taiwan University of Science and Technology (NTUST), Taiwan.

💼 Work Experience

• Amazon — Amazon Quick — Applied Scientist Intern, Seattle, WA. Sep. 2026–Present
  • Build an end-to-end multi-agent software generation system for Amazon Quick, integrating task planning, code synthesis, tool orchestration, and execution to automate sandbox environment creation.
  • Optimize tool selection and invocation, agent memory and retrieval, multi-agent communication topology, execution harnesses, and loop engineering through self-improving workflows and recursive self-improvement (RSI).
• GEICO — Research & Innovation — Data Scientist, Chevy Chase, MD. Jan. 2022–Dec. 2023
  • Built an automatic multimodal document-verification pipeline that fuses textual information and visual patterns via a BERT and CNN fusion model, achieving 98% overall accuracy for insurance customer verification.
  • Designed and deployed an underwriting ML pipeline to detect potential insurance fraud, reducing the overall loss ratio by 3.5% and generating projected annual savings of $60M.

🤝 Professional Service

Program Committee / Reviewer: ACL 2026, ACL 2026 Industry Track, ICML 2026, NeurIPS 2026.