🤖 AI Summary
This work addresses the performance limitations of general-purpose generative agents in industrial settings due to insufficient domain-specific knowledge. To overcome this challenge, the authors propose a domain-enhanced generative agent framework that uniquely integrates structured knowledge retrieval with a human-in-the-loop persistent memory mechanism. The framework enables task-specific prior injection, loading of private knowledge bases, and storage of expert tacit knowledge, while supporting fully privatized deployment. Empirical evaluations across text generation tasks in healthcare, finance, and industrial domains demonstrate that the proposed approach significantly outperforms existing baseline methods, thereby validating its cross-domain applicability and effectiveness.
📝 Abstract
Despite the rapid advancement of generative agents, their deployment in real-world industry scenarios often encounters significant challenges due to a lack of domain-specific knowledge. To address this gap, we present KnowPilot: a Domain-Specific Knowledge Augmented Generative Agent System. KnowPilot is an open-source framework that integrates task-specific priors, explicit knowledge, and experiential knowledge to enhance agent performance in specialized applications. It combines knowledge retrieval from structured repositories with a memory system capable of capturing expert experience through human AI interaction. Taking domain-specific writing generation as a representative case, KnowPilot enables private deployment, supports injection of task requirements, loads private knowledge bases, and stores tacit expert knowledge as persistent memory. Experimental results demonstrate that KnowPilot achieves superior performance in domain-oriented text generation and is applicable across fields such as medicine, finance and industry.