← Search

Woosog Chay

2 accepted papers

2026

From Conversation to Query Execution: Benchmarking User and Tool Interactions for EHR Database Agents

ICLR 2026poster

Despite the impressive performance of LLM-powered agents, their adoption for Electronic Health Record (EHR) data access remains limited by the absence of benchmarks that adequately capture real-world clinical data access flows. In practice, two core challenges hinder deployment: query ambiguity from…

Cited by 0SourcecodeScholar
2026

ProPerSim: Developing Proactive and Personalized AI Assistants through User-Assistant Simulation

ICLR 2026poster

As large language models (LLMs) become increasingly integrated into daily life, there is growing demand for AI assistants that are not only reactive but also proactive and personalized. While recent advances have pushed forward proactivity and personalization individually, their combination remains…

Cited by 0SourceScholar