4 papers
Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls
Zeyu Zhang, Guohao Li, Zhenchang Xing +3
The ability to use tools is fundamental for large language model (LLM) agents. Given a task, existing systems use LLMs to plan and generate tool calls, which are executed by real-w…
Clinical Knowledge Graph Construction and Evaluation with Multi-LLMs via Retrieval-Augmented Generation
Udiptaman Das, Krishnasai B. Atmakuri, Duy Ho +2
Large language models (LLMs) offer new opportunities for constructing knowledge graphs (KGs) from unstructured clinical narratives. However, existing approaches often rely on struc…
PathFormer: A Transformer with 3D Grid Constraints for Digital Twin Robot-Arm Trajectory Generation
Ahmed Alanazi, Duy Ho, Yugyung Lee
Robotic arms require precise, task-aware trajectory planning, yet sequence models that ignore motion structure often yield invalid or inefficient executions. We present a Path-base…
GRIP: A Unified Framework for Grid-Based Relay and Co-Occurrence-Aware Planning in Dynamic Environments
Ahmed Alanazi, Duy Ho, Yugyung Lee
Robots navigating dynamic, cluttered, and semantically complex environments must integrate perception, symbolic reasoning, and spatial planning to generalize across diverse layouts…