DySRec: Dynamic Context-Aware Psychometric Scale Recommendation via Multi-Agent Collaboration

2026-05-01

AI Summary

Existing psychological scale recommendation systems predominantly rely on static workflows or direct symptom prediction, limiting their capacity for dynamic assessment, risk monitoring, and transparent decision-making. This work proposes the first multi-agent collaborative dialogue-based recommendation system that jointly models user semantics, behavior, assessment history, and dialogue state through multi-turn interactions to dynamically update user representations and compute scale-context compatibility. By integrating dialogue state tracking, dynamic representation learning, compatibility scoring, and a closed-loop feedback mechanism, the system effectively fuses heterogeneous signals in real-world scenarios. This approach not only enhances the personalization and adaptability of recommendations but also improves decision transparency and proactively identifies and fills critical missing information.

Abstract

Choosing suitable psychometric scales is an essential and difficult step in psychological consultation, which requires clinicians to integrate patient information, behaviors, and dynamic contextual information. Existing systems mainly use static pipelines to choose scale, or directly predict symptoms according to user inputs, limiting their ability to support dynamic assessment, risk management, and transparent decision-making. To address these limitations, we propose DySRec, a multi-agent conversational system for dynamic psychometric scale recommendation. DySRec operates as an interactive chatbot that engages users in multi-turn dialogue, models scale selection as a continuous conversational decision process, and coordinates specialized agents to maintain user context, recommend assessment scales, monitor psychological risk, and log decision trajectories. In this way, DySRec can integrate and capture heterogeneous signals, including semantic, interaction behaviors, assessment history, and content state, to dynamically update user representations and calculate scale-context compatibility score for recommending most matched scales. Moreover, DySRec incorporates a closed-loop refinement mechanism. Recommendation agent will feedback the missing or uncertain attributes and guide the conversation to elicit the targeted information. In this paper, we showcase the prototype design and architecture of DySRec, and this system has been verified in a real-world application.

Problem

• psychometric scale recommendation
• dynamic context
• psychological assessment
• multi-agent system
• conversational AI

Innovation

• multi-agent collaboration
• dynamic context-aware recommendation
• psychometric scale selection
• conversational decision process
• closed-loop refinement