Selected work
The work moves from measured decisions to model structure, agent behavior, constraint checks, and consequences in a coupled environment.
Selected work
Each project shows a different part of the same practice: evaluating decisions, tracing their consequences, and governing when they may alter a system.
Compare LLM-generated decisions with measured human pathways across social groups.
I designed the human-versus-model comparison, subgroup lenses, and repeated-run stability checks.
Connect household adaptation to flood damage, insurance, and financial exposure.
I built the household decision model and connected adaptation choices to catastrophe, insurance, and financial mechanics.
Check and repair agent decisions before they update a coupled simulation.
I designed the validation and repair path that checks an agent proposal before the simulation state can change.
Open-source systems proof
Selected repositories support research operations, agent orchestration, and multilingual learning. Counts are refreshed through a reviewed build-time data workflow.
Maintained trilingual roadmap for agentic AI, with automated cross-language checks.
6.2K stars · 836 forks
awesome-agentic-ai-zhComposable research workflow from gap discovery through study design and drafting.
220 stars · 17 forks
ai-research-skillsLocal-first Zotero, Obsidian, and NotebookLM workspace with provenance checks.
52 stars · 8 forks
research-hubTask splitting, reconciliation, debate, and acceptance gates for multi-agent work.
23 stars · 6 forks
agent-collab-skillsCross-platform delegation wrapper that verifies completion from repository state.
63 stars · 6 forks
codex-delegateUpdated: 2026-08-23 · Source: GitHub REST API snapshot
Choose the document for the context. The website keeps one identity; the PDFs change emphasis for the reader.
Contact
I am seeking a full-time Summer 2027 internship from approximately late May through mid-August. I am especially interested in LLM evaluation, agent systems, behavioral simulation, and AI for science.