Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support

• URL: http://arxiv.org/abs/2606.30887v1
• Date: Mon, 29 Jun 2026 20:22:25 GMT
• Title: Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support
• Abstract summary: We introduce a framework that formulates therapeutic response generation as a decision-refinement problem driven by human-aligned evaluation.<n>In Stage I, we introduce TheraJudge, an open-source therapeutic evaluator trained via preference-based optimization on human-annotated data.<n>In Stage II, we introduce TheraAgent, which operationalizes TheraJudge's evaluations through a coordinated refinement process.
• Score: 22.031194303408792
• License: http://creativecommons.org/licenses/by/4.0/
• 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. We introduce a framework that formulates therapeutic response generation as a decision-refinement problem driven by multi-dimensional, human-aligned evaluation. In Stage I, we introduce TheraJudge, an open-source therapeutic evaluator trained via preference-based optimization on human-annotated data to produce reliable judgments across 7 psychological dimensions. In Stage II, we introduce TheraAgent, which operationalizes TheraJudge's evaluations through a coordinated refinement process with specialized Critic, Coach, and Therapist roles that translate evaluative signals into targeted response revisions. Empirically, TheraJudge achieves strong agreement with clinician ratings, with intraclass correlation coefficients (ICC = 0.87-0.95), surpassing supervised baselines and strong closed-source judges, particularly on critical dimensions such as Safety, Relevance, and Empathy. Acting on these evaluations, TheraAgent yields a +0.43 improvement in human-rated therapeutic quality (on a 5-point scale) under blind evaluation, with 96\% clinician inter-rater reliability. Low-quality responses ($\leq 3$) improve by +2.45 points with a 94\% recovery rate, demonstrating targeted correction of unsafe outputs. Overall, our results indicate that effective alignment of mental-health LLMs stems from acting on human-aligned evaluation, rather than relying solely on stronger generation. We release code at https://github.com/vis-nlp/TheraAlign.

Related papers

• A Multi-Agent LLM Framework for Rating the Quality of Surgical Feedback [52.053200111780626]
  Verbal feedback delivered by attending surgeons in the operating room plays a critical formative role in resident skill acquisition.<n>We introduce a two-stage LLM-based framework that discovers interpretable feedback quality criteria grounded in the context of surgical training.<n>Our method uses multi-agent and surgical domain knowledge injection to discover a small set of human interpretable scoring criteria.
  arXiv  Detail & Related papers  (2026-05-25T05:31:44Z)
• Speech-based Psychological Crisis Assessment using LLMs [15.893490778343198]
  This paper proposes a large language model (LLM)-based framework for automated crisis level classification.<n>To better capture emotional signals in spoken conversations, we introduce a paralinguistic injection method.
  arXiv  Detail & Related papers  (2026-05-11T05:50:51Z)
• Detecting Stealth Sycophancy in Mental-Health Dialogue with Dynamic Emotional Signature Graphs [4.002154823241671]
  We study multi-domain support-dialogue evaluation without relying on large language models as final judges.<n>We find that direct LLM judges and symmetric text-similarity metrics are poorly aligned with therapeutic quality.<n>To address this issue, we propose Dynamic Emotional Signature Graphs (DESG)<n>DESG represents dialogue windows with decoupled clinical states and scores them using asymmetric clinical geometry.
  arXiv  Detail & Related papers  (2026-05-05T07:56:20Z)
• TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots [24.894881768337125]
  THERAPYGYM is a framework that evaluates and improves therapy chatbots along two clinical pillars: fidelity and safety.<n>To mitigate bias and unreliability in LLM-based judges, we release THERAPYJUDGEBENCH, a validation set of 116 dialogues with 1,270 expert ratings.
  arXiv  Detail & Related papers  (2026-02-23T06:05:01Z)
• Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation [56.84819098277464]
  CoNL is a framework that unifies generation, evaluation, and meta-evaluation through multi-agent self-play.<n>CoNL achieves consistent improvements over self-rewarding baselines while maintaining stable training.
  arXiv  Detail & Related papers  (2026-01-29T09:41:14Z)
• Assessing the Quality of Mental Health Support in LLM Responses through Multi-Attribute Human Evaluation [14.243791046586347]
  The escalating global mental health crisis, marked by persistent treatment gaps, availability, and a shortage of qualified therapists, positions Large Language Models (LLMs) as a promising avenue for scalable support.<n>This paper introduces a human-grounded evaluation methodology designed to assess LLM generated responses in therapeutic dialogue.
  arXiv  Detail & Related papers  (2026-01-26T16:04:19Z)
• Automated Rubrics for Reliable Evaluation of Medical Dialogue Systems [19.880569341968023]
  Large Language Models (LLMs) are increasingly used for clinical decision support, where hallucinations and unsafe suggestions may pose direct risks to patient safety.<n>We propose a retrieval-augmented multi-agent framework designed to automate the generation of instance-specific evaluation rubrics.
  arXiv  Detail & Related papers  (2026-01-21T16:40:41Z)
• DispatchMAS: Fusing taxonomy and artificial intelligence agents for emergency medical services [49.70819009392778]
  Large Language Models (LLMs) and Multi-Agent Systems (MAS) offer opportunities to augment dispatchers.<n>This study aimed to develop and evaluate a taxonomy-grounded, multi-agent system for simulating realistic scenarios.
  arXiv  Detail & Related papers  (2025-10-24T08:01:21Z)
• Ψ-Arena: Interactive Assessment and Optimization of LLM-based Psychological Counselors with Tripartite Feedback [51.26493826461026]
  We propose Psi-Arena, an interactive framework for comprehensive assessment and optimization of large language models (LLMs)<n>Arena features realistic arena interactions that simulate real-world counseling through multi-stage dialogues with psychologically profiled NPC clients.<n>Experiments across eight state-of-the-art LLMs show significant performance variations in different real-world scenarios and evaluation perspectives.
  arXiv  Detail & Related papers  (2025-05-06T08:22:51Z)
• Pairwise or Pointwise? Evaluating Feedback Protocols for Bias in LLM-Based Evaluation [57.380464382910375]
  We show that the choice of feedback protocol for evaluation can significantly affect evaluation reliability and induce systematic biases.<n>We find that generator models can flip preferences by embedding distractor features.<n>We offer recommendations for choosing feedback protocols based on dataset characteristics and evaluation objectives.
  arXiv  Detail & Related papers  (2025-04-20T19:05:59Z)
• Opportunities of a Machine Learning-based Decision Support System for Stroke Rehabilitation Assessment [64.52563354823711]
  Rehabilitation assessment is critical to determine an adequate intervention for a patient. Current practices of assessment mainly rely on therapist's experience, and assessment is infrequently executed due to the limited availability of a therapist. We developed an intelligent decision support system that can identify salient features of assessment using reinforcement learning.
  arXiv  Detail & Related papers  (2020-02-27T17:04:07Z)

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.