An Agentic LLM-Based Framework for Population-Scale Mental Health Screening

2026-05-13

AI Summary

This study addresses the urgent need for trustworthy, reproducible, and individualized intelligent frameworks in global mental health screening amid surging demand and clinical data overload. The authors propose a large language model–based multi-agent screening framework that employs strategy-constrained LangChain agents operating in sequential stages, augmented by a coordinator agent and a stage-locking mechanism to ensure configuration stability, traceability, and adaptability. By integrating proxy-guided evaluation, dynamic Top-k retrieval, cosine similarity matching, and threshold optimization, the framework converges to a stable and efficient configuration—such as a similarity threshold of 0.75—in interview-based depression detection tasks. This approach significantly enhances screening reliability and reproducibility while effectively controlling evaluation costs and mitigating performance degradation.

Abstract

Mental health disorders affect millions worldwide, and healthcare systems are increasingly overwhelmed by the volume of clinical data generated from electronic records, telemedicine platforms, and population-level screening programs. At the same time, the emergence of novel AI-based approaches in healthcare calls for intelligent frameworks capable of processing domain-specific unstructured clinical information while adapting to patient-specific needs. This paper proposes an agentic framework for building robust LLM-based pipelines, where each stage is encapsulated as a LangChain agent governed by explicit policies and proxy-guided evaluation. Stages are incrementally locked once validated, ensuring that later adaptations cannot overwrite configurations without demonstrated improvement. The proposed framework evolves from feature-level exploration, through proxy-based tuning and freeze/rollback mechanisms, to full orchestration by an Orchestrator Agent that coordinates preprocessing, retrieval, selection, diversity, threshold optimization, and decoding. A proof-of-concept in transcript-based depression detection demonstrates that the framework converges to stable configurations, such as cosine similarity, dynamic Top-k, and threshold 0.75, while controlling evaluation costs and avoiding regressions. These results highlight the potential of agentic AI to enable population-level mental health screening over large clinical datasets, addressing critical challenges in trustworthiness, reproducibility, and adaptability required in healthcare environments.

Problem

• mental health screening
• population-scale
• clinical data
• trustworthiness
• adaptability

Innovation

• Agentic AI
• LLM-based framework
• Proxy-guided evaluation
• Orchestrator Agent
• Population-scale mental health screening