Tag
This paper studies orchestration mechanisms for tool-using AI agents in customer-service workflows, comparing declarative agents with imperative state machines and baselines. Results show retrieval quality is a key bottleneck, and under high-quality retrieval, declarative skills improve accuracy on procedural tasks.
Introduces SafeRx-Agent, a knowledge-grounded multi-agent framework for safe and explainable medication recommendation that generates fine-grained ATC code predictions while controlling drug interactions and contraindications, evaluated on MIMIC-III and MIMIC-IV datasets.
This paper presents a framework that uses domain-specific expert knowledge to ground large language models for providing Just-in-Time adaptive feedback to students based on their written reasoning, achieving over 80% improvement in student performance in a large university course.