arXiv AI
Jun 17
Mental Health AI Safety Claims Must Preserve Temporal Evidence
arXiv:2605. 08827v2 Announce Type: replace Abstract: The safety of mental health AI is often judged at the wrong temporal scale.
PAIR-SAFE: A Paired-Agent Approach for Runtime Auditing and Refining AI-Mediated Mental Health Support
PAIR‑SAFE is a paired‑agent framework that pairs a Responder agent with a Judge agent grounded in the clinically validated Motivational Interviewing Treatment Integrity (MITI‑4) to audit and refine AI‑mediated mental health support in real time. The Judge evaluates each response and issues “allow” or “revise” decisions, guiding the Responder toward more clinically aligned interactions. Experiments with a support‑seeker simulator show that Judge‑supervised interactions significantly improve MITI dimensions such as Partnership, Seek Collaboration, and overall relational quality, with findings corroborated by expert evaluation.
Related stories
arXiv AI
Jul 1
Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support
arXiv:2606. 30887v1 Announce Type: cross Abstract: Large language models show promise for mental health support, yet therapeutic quality improves only when evaluation functions as an actionable control signal rather than a passive metric.
arXiv AI
Sep 21
Clinician-Grounded Quality Assurance for AI-Assisted Psychiatric Intake
The paper introduces a clinician‑grounded evaluation platform called InterviewPlayground, which uses a memory‑augmented patient simulator to assess AI‑assisted psychiatric intake systems. It supports comparison across different interviewing styles, reduces clinician workload, and measures clinically relevant performance. In a pilot study, a GPT‑based intake interviewer captured more relevant items but made more unfounded inferences and missed safety concerns compared to clinicians.
arXiv AI
Jul 29
PatientAgentBench: A Benchmark Framework for Evaluating Patient-Facing Health AI Agents
arXiv:2607. 25485v1 Announce Type: new Abstract: Health AI is evolving from answering questions to agentic systems that converse with patients, reason about health records, and act on their behalf.
arXiv AI
Sep 1
MAGneT: Coordinated Multi-Agent Generation of Synthetic Multi-Turn Mental Health Counseling Sessions
arXiv:2509.04183v3 Announce Type: replace-cross Abstract: The growing demand for scalable psychological counseling highlights the need for high-quality, privacy-compliant data, yet such data remains...
arXiv AI
Oct 7
PsyCIDRA: A Dual-Agent Framework for Psychiatric Interviewing and Diagnostic Reasoning
PsyCIDRA is a dual‑agent framework that couples a free‑form psychiatric interviewer with a diagnostic reasoning agent to support expert review. The interviewer agent uses tools to keep working notes, load expert skills, and pull ICD‑11 references, while the diagnostic agent receives the interview transcript and generates hypotheses with supporting, conflicting, and missing evidence, withholding a final hypothesis if insufficient support exists. In simulations and a blinded human study, PsyCIDRA achieved higher diagnostic agreement and rank‑1 accuracy than direct prompting, indicating its promise for assisting psychiatric assessment through interactive dialogue.
arXiv AI
Oct 7
MASC: A Multi-Agent Self-Calibration Framework with Latent Construct Alignment for Consistent Client Role-Playing in Psychological Counseling
arXiv:2610.08250v1 Announce Type: new Abstract: Large language models are increasingly used to simulate clients for counselor training and psychological counseling research, but reliable simulation r...
arXiv AI
Jul 15
First, do NOHARM: a medical safety benchmark and randomized study of physician and AI teaming on clinical consultations
arXiv:2512. 01241v4 Announce Type: replace-cross Abstract: Large language models (LLMs) and medical AI tools are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain poorly characterized.
arXiv Computation and Language
Sep 18
CounselReflect: Opportunities and Challenges for Designing Tools to Support Self-Reflection on Mental Health and Well-Being Conversations with AI
The paper introduces CounselReflect, a tool that converts counseling quality metrics into a framework for users to reflect on their mental‑health AI conversations. Through interviews with 21 users, the study finds that while most participants rarely reflect on their interactions, they identify specific questions they would like such a tool to address. The findings also reveal that users tend to confirm existing beliefs and focus on familiar dimensions, highlighting the need for reflection tools to expose blind spots and encourage a more comprehensive examination of AI interactions, especially when revisiting emotionally charged exchanges.
arXiv Computation and Language
Aug 24
Trust Stack for Mental Health AI: A Survey of Calibration across Human, Interaction, and AI Layers
The paper surveys 61 studies on mental‑health AI and identifies a misalignment in how trust is evaluated across disciplines. It proposes a three‑layer framework—human‑oriented, interaction‑oriented, and AI‑oriented trust—and maps stakeholder perspectives onto these layers. The authors argue that future research should focus on calibrating human trust to actual interaction and AI trustworthiness rather than merely maximizing perceived trust.
arXiv AI
Sep 3
Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning
The paper investigates how human interventions at specific fault points—moments when an AI agent’s reasoning is most vulnerable—affect the diagnostic accuracy of multi‑agent medical systems. Using the MedQA dataset, the authors found that correct interventions can boost baseline accuracy by up to 40%, whereas incorrect or bias‑related interventions can reduce performance by up to 6% and increase diagnostic drift and uncertainty. The study also highlights behavioral parallels between cognitive biases observed in simulated agent conversations and real‑world clinical practice, such as premature closure and susceptibility to misleading cues.
arXiv AI
Jun 2
Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration
arXiv:2605. 09366v3 Announce Type: replace Abstract: Transforming neuroimaging data into clinically actionable biomarkers is a knowledge-intensive and labor-intensive process.