CPEMH: An Agentic Framework for Prompt-Driven Behavior Evaluation and Assurance in Foundation-Model Systems for Mental Health Screening

• URL: http://arxiv.org/abs/2605.11341v1
• Date: Mon, 11 May 2026 23:52:01 GMT
• Title: CPEMH: An Agentic Framework for Prompt-Driven Behavior Evaluation and Assurance in Foundation-Model Systems for Mental Health Screening
• Abstract summary: CPEMH serves as an engineering methodology for behavioral assurance in large-scale language systems.<n>Its modular agentic design, combining orchestrator, inference, and evaluation agents, ensures traceability, robustness, and robustness throughout the prompting lifecycle.
• Score: 0.326654570054705
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper presents CPEMH, an agentic framework designed to evaluate prompt-driven behavior in foundation-model systems operating on transcript-based datasets for mental-health screening. CPEMH serves as an engineering methodology for behavioral assurance in large-scale language systems, introducing an orchestrated architecture that autonomously performs the design, evaluation, and selection of prompt strategies, enabling systematic control of behavioral variability across contexts. Its modular agentic design, combining orchestrator, inference, and evaluation agents, ensures traceability, reproducibility, and robustness throughout the prompting lifecycle. A case study on automated depression screening from interview transcripts demonstrates the framework's capacity to stabilize and audit foundation-model behavior in conversational and clinically sensitive domains. Lessons learned emphasize the role of modular orchestration in behavioral assurance, the prioritization of stability over architectural complexity, and the integration of F1, bias, and robustness as core acceptance criteria.

Related papers

• Three Generations of Healthcare IT: From the Digital Record to the Computable Care Process [47.027290803102666]
  We describe a computational layer whose object is patient-specific clinical intent.<n>We formalize the Actionable Clinical Record as the atomic object of the third layer.
  arXiv  Detail & Related papers  (2026-08-09T16:44:28Z)
• CyberAGENTS: Structured Autonomy for Agentic Gamified Learning in Cybersecurity [9.5902083024001]
  Gamification is especially effective in learning domains requiring active problem-solving and iterative skill-building.<n>Generative AI agents offer a path to delivering such experiences adaptively at scale, but introduce well-documented risks in educational settings.<n>We present model, an agentic framework for gamified cybersecurity learning.
  arXiv  Detail & Related papers  (2026-08-08T06:59:45Z)
• Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems [64.88044474617854]
  The rapid integration of large language model-based agents into recommender systems has driven a shift from static, ranking-based pipelines toward autonomous and interactive systems.<n>This survey introduces a unified taxonomy grounded in the level of autonomy and three core paradigms of agentic recommender systems.
  arXiv  Detail & Related papers  (2026-07-05T17:55:05Z)
• From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape [79.30826980815927]
  rubrics are explicit criteria sets that transform complex quality judgments into structured and actionable standards.<n>We systematically organize existing rubric designs, examine their construction and optimization, and analyze their role across evaluation and training.
  arXiv  Detail & Related papers  (2026-06-07T13:34:55Z)
• The Model Is Not the Product: A Dual-Pillar Architecture for Local-First Psychological Coaching [51.56484100374058]
  This report introduces Psych LM, an iOS application that validates the thesis that, for such applications, the surrounding architecture is paramount.<n>Psych LM runs a local, on-device language model within a purpose-built, local-first runtime designed for behavioral and life-coaching applications.
  arXiv  Detail & Related papers  (2026-05-23T05:49:11Z)
• An Agentic LLM-Based Framework for Population-Scale Mental Health Screening [0.3568466510804538]
  This paper proposes an agentic framework for building robust LLM-based pipelines.<n>A proof-of-concept in transcript-based detection demonstrates that the framework converges to stable configurations.<n>Results highlight the potential of agentic AI to enable population-level mental health screening over large clinical datasets.
  arXiv  Detail & Related papers  (2026-05-13T06:08:43Z)
• From Black-Box Confidence to Measurable Trust in Clinical AI: A Framework for Evidence, Supervision, and Staged Autonomy [0.0]
  Trust in clinical artificial intelligence (AI) cannot be reduced to model accuracy, fluency of generation, or overall positive user impression.<n>This article proposes a framework for trustworthy clinical AI built around three principles: evidence, supervision, and staged autonomy.
  arXiv  Detail & Related papers  (2026-04-29T13:40:14Z)
• A Safety-Aware Role-Orchestrated Multi-Agent LLM Framework for Behavioral Health Communication Simulation [0.0]
  Single-agent large language model (LLM) systems struggle to simultaneously support diverse conversational functions and maintain safety in behavioral health communication.<n>We propose a safety-aware, role-orchestrated multi-agent LLM framework designed to simulate supportive behavioral health dialogue through coordinated, role-differentiated agents.
  arXiv  Detail & Related papers  (2026-03-31T21:21:31Z)
• Toward Clinically Ready Foundation Models in Medical Image Analysis: Adaptation Mechanisms and Deployment Trade-offs [4.332241609032423]
  This review introduces a strategy-centric framework for FM adaptation in medical image analysis (MIA)<n>We conceptualize adaptation as a post-pretraining intervention and organize existing approaches into five mechanisms.<n>For each mechanism, we analyze trade-offs in adaptation depth, label efficiency, domain robustness, computational cost, auditability, and regulatory burden.
  arXiv  Detail & Related papers  (2026-03-15T08:04:58Z)
• SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions [0.0]
  This paper provides the first unified framework for understanding these autonomous systems.<n>We formalize agentic retrieval-generation loops as finite-horizon partially observable Markov decision processes.<n>We identify severe systemic risks inherent to autonomous loops, including compounding hallucination propagation, memory poisoning, retrieval misalignment, and cascading tool-execution vulnerabilities.
  arXiv  Detail & Related papers  (2026-03-07T23:38:57Z)
• QCAgent: An agentic framework for quality-controllable pathology report generation from whole slide image [44.81983055985989]
  QCAgent is an agentic framework for quality-controllable pathology report generation from whole-slide image (WSI)<n>It incorporates a customized critique mechanism guided by a user-defined checklist specifying required diagnostic details and constraints.<n>It re-identifies informative regions in the WSI based on the critique feedback and text-patch semantic retrieval.
  arXiv  Detail & Related papers  (2026-03-02T09:27:31Z)
• TRACE: Temporal Reasoning via Agentic Context Evolution for Streaming Electronic Health Records (EHRs) [7.2159153945746795]
  Large Language Models (LLMs) encode extensive medical knowledge but struggle to apply it reliably to longitudinal patient trajectories.<n>We introduce TRACE, a framework that enables temporal clinical reasoning with frozen LLMs.<n> evaluated on longitudinal clinical event streams from MIMIC-IV.
  arXiv  Detail & Related papers  (2026-02-13T11:39:19Z)
• Technical Report: Facilitating the Adoption of Causal Inference Methods Through LLM-Empowered Co-Pilot [44.336297829718795]
  We introduce CATE-B, an open-source co-pilot system that uses large language models (LLMs) within an agentic framework to guide users through treatment effect estimation.<n>CATE-B assists in (i) constructing a structural causal model via causal discovery and LLM-based edge orientation, (ii) identifying robust adjustment sets through a novel Minimal Uncertainty Adjustment Set criterion, and (iii) selecting appropriate regression methods tailored to the causal structure and dataset characteristics.
  arXiv  Detail & Related papers  (2025-08-14T12:20:51Z)
• A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems [53.37728204835912]
  Most existing AI systems rely on manually crafted configurations that remain static after deployment.<n>Recent research has explored agent evolution techniques that aim to automatically enhance agent systems based on interaction data and environmental feedback.<n>This survey aims to provide researchers and practitioners with a systematic understanding of self-evolving AI agents.
  arXiv  Detail & Related papers  (2025-08-10T16:07:32Z)
• A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents [45.53643260046778]
  Recent advances in large language models (LLMs) have catalyzed the rise of autonomous AI agents.<n>These large-model agents mark a paradigm shift from static inference systems to interactive, memory-augmented entities.
  arXiv  Detail & Related papers  (2025-06-30T13:34:34Z)
• Quantifying Robustness: A Benchmarking Framework for Deep Learning Forecasting in Cyber-Physical Systems [44.61435605872856]
  We introduce a practical robustness definition grounded in distributional robustness, explicitly tailored to industrial CPS.<n>Our framework simulates realistic disturbances, such as sensor drift, noise and irregular sampling, enabling thorough robustness analyses of forecasting models.
  arXiv  Detail & Related papers  (2025-04-04T14:50:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.