Research
Published work on trustworthy agentic AI.
Peer-reviewed and preprint research spanning voice agents, frontier agent architectures, graph data systems, and GenAI planning robustness.
Publications
Papers
2025
Confidence-Gated Hybrid SLM-LLM with Context Lake and Feedback for Low-Latency Insurance Voice Agents
View on Google Scholar →
2025
Self-Improving Frontier Agents for Insurance Operations: A Governed Architecture for Autonomous Claims Reasoning and Workflow Adaptation
View on Google Scholar →
2026
Unified Graph Query Engine for Heterogeneous Databases: Enabling High-Performance Graph Queries Without Data Migration
View on Google Scholar →
2026
Volatility Modeling Using GARCH and Machine Learning Hybrids
View on Google Scholar →
2026
Generative AI Planning Robustness
View on Google Scholar →
Themes
Research directions
THEME
Low-Latency Voice Agents
Confidence-gated hybrid SLM-LLM architectures with context lakes and feedback loops for insurance-grade voice agents.
THEME
Governed Autonomous Agents
Self-improving frontier agents for claims reasoning and workflow adaptation — autonomy with oversight.
THEME
Data & Planning Foundations
Unified graph query engines across heterogeneous databases, GARCH-ML volatility hybrids, and GenAI planning robustness.
Get started
Research collaboration or review?
Open to co-authorship, program committees, and applying research to production problems.