Educational-Psychological Dialogue Robot Based on Multi-Agent Collaboration

TL;DR

This work tackles the limitation of single-domain dialogue systems by proposing a multi-agent educational counseling framework that combines retrieval-augmented educational reasoning with psychology-focused dialogue, guarded by a security filter and driven by an intent classifier to route interactions. The Educational LLM Agent uses a Baidu Encyclopedia vector store with Faiss HNSW indexing and a reranker, fine-tuned on COIG-CQIA, to deliver rapid, context-rich educational answers, while the Psychological LLM Agent is refined with counseling data to handle psychological support. Experiments on the E-Eval Chinese K-12 benchmark show the system often surpasses GPT-4 in several subjects and consistently outperforms other baselines, validating cross-domain efficacy and safety. The proposed multi-agent collaboration offers a practical path to comprehensive educational and psychological support in intelligent tutoring and counseling contexts, with potential for deployment in real-world educational and counseling settings.

Abstract

Intelligent dialogue systems are increasingly used in modern education and psychological counseling fields, but most existing systems are limited to a single domain, cannot deal with both educational and psychological issues, and often lack accuracy and professionalism when dealing with complex issues. To address these problems, this paper proposes an intelligent dialog system that combines educational and psychological counseling functions. The system consists of multiple AI agent, including security detection agent, intent identification agent, educational LLM agent, and psychological LLM agent, which work in concert to ensure the provision of accurate educational knowledge Q\&A and psychological support services. Specifically, the system recognizes user-input intentions through an intention classification model and invokes a retrieval-enhanced educational grand model and a psychological grand model fine-tuned with psychological data in order to provide professional educational advice and psychological support.

Figures (1)

• Figure 1: A figure caption is always placed below the illustration. Please note that short captions are centered, while long ones are justified by the macro package automatically.