Lifelong Agent Memory
How agents turn individual experiences into reliable shared procedures, with scope-aware promotion, evidence gates, and resistance to memory poisoning.

Research · Official Researcher Profile
Researcher in AI Systems
I study how AI agents learn from experience and interact with the systems around them. My work focuses on reliable memory for lifelong agents, documentation and interfaces for agent programming, and AI tools for scientific discovery and health. I connect these questions with my background in software engineering, secure systems, and computer vision.
How agents turn individual experiences into reliable shared procedures, with scope-aware promotion, evidence gates, and resistance to memory poisoning.
How documentation, interface design, and tool access affect code generation and correctness, including controlled studies of StableHLO.
Evidence mapping for scientific research and digital phenotyping for neurodegenerative disease detection.
Accepted poster · 3rd Workshop on Lifelong Agents (AIAS 2026)
Luxin Zhang · November 7, 2026 · DOI: 10.5281/zenodo.24063133
ScopeAware turns successful agent experiences into shared procedures only when the evidence is reliable and the scope is explicit. Across enterprise support and scientific-facility evaluations, it improves resolution accuracy while sharply reducing harmful memory promotion.
View paper details →Accepted poster · VISA 2026 at IEEE/ACM MICRO 2026
Luxin Zhang · November 2026 · DOI: 10.5281/zenodo.24062377
A controlled study of how documentation format and delivery affect AI agents programming StableHLO. Syntax alone produces large gains, while matched prose outperforms JSON contracts and upfront documentation consistently beats on-demand retrieval.
View paper details →Research Paper
Hypothesis Atlas introduces an open-source, hypothesis-first evidence mapping workflow that retrieves live papers, datasets, and early signals, then surfaces disagreements, gaps, and research opportunities through epistemically-labeled synthesis.
Read More →Book Chapter
A book chapter exploring digital phenotyping approaches using mandala-based assessments for early detection of neurodegenerative diseases, published in 'Where Art and Technology Resonate: Binnovative Approaches to Digital Health and Wellbeing'.
Read More →AI-powered evidence mapping system for biotech research that discovers, organizes, and visualizes signals from papers, datasets, and scientific updates.
View Repository →Reviewer
EvalScience
November 2026 · New York, New York
Official website ↗Reviewer
WORTH 2027
November 2026 · Tucson, Arizona
Official website ↗Reviewer
SAFE Workshop
November 2026 · Montréal, Québec
Official website ↗Program Committee Member (Reviewer)
Association for the Advancement of Artificial Intelligence
October 8–14, 2026 · Palo Alto, California
Official website ↗Reviewer
Association of Schools and Programs of Public Health
October 2026 · Washington, District of Columbia
Official website ↗Reviewer
Association for Computational Linguistics
July 22–24, 2026 · Stroudsburg, Pennsylvania
Official website ↗