KnowledgeBot is a conversational embodied agent developed by Virginia Tech for the Alexa Prize SimBot Challenge. It is designed to assist users in completing a wide range of daily tasks through natural and interactive dialogue. By integrating neuro-symbolic reasoning, KnowledgeBot effectively processes user instructions and environmental perceptions to perform actions and provide responses. Key Features and Functionality: - Neuro-Symbolic Reasoning: Combines symbolic reasoning with neural-based action planning and prediction modules to interpret and execute complex tasks. - Vision Models: Utilizes semantic segmentation and visual grounding to comprehend and interact with the environment effectively. - Situated Dialogue Module: Facilitates natural and context-aware conversations with users, enhancing the interactive experience. - Task Execution: Capable of carrying out a variety of user-defined tasks by understanding instructions and environmental cues. Primary Value and User Solutions: KnowledgeBot addresses several challenges in the development of intelligent assistive agents, including the vast variety of user-defined tasks, the need for complex reasoning and visual comprehension, and the importance of natural human interaction. By integrating advanced reasoning and vision capabilities, KnowledgeBot offers users an efficient and intuitive assistant for daily task completion, enhancing productivity and user experience.