LLM Agents
LLM Agents
I study how LLM-based systems search, expose, retrieve, evaluate, and govern capabilities when they become reusable infrastructure.
Evaluation before dependency
How can agent capabilities and search policies be selected, inspected, and evaluated before they become production dependencies?
Scope
AI search, skill retrieval, NL2SQL benchmarks, LLM serving systems, and capability governance are treated as system surfaces that should be inspected before they are trusted.
AI search
Keeping search policies aligned with changing inventory and evidence conditions.
Skill retrieval
Evaluating ambiguity when multiple skills expose similar capabilities and must be selected reliably.
Capability governance
Studying how reusable agent capabilities are represented, selected, exposed, and evaluated.
NL2SQL and serving
Benchmarking business intelligence services and scaling LLM inference systems.