Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support
This paper proposes a framework for therapeutic response generation driven by multi-dimensional, human-aligned evaluation. Stage I introduces TheraJudge, an open-source therapeutic evaluator trained via preference-based optimization on human-annotated data, producing reliable judgments across 7 psychological dimensions. Stage II introduces TheraAgent, which operationalizes the evaluations through a coordinated refinement process with Critic, Coach, and Therapist roles. TheraJudge achieves strong agreement with clinician ratings (ICC=0.87-0.95), and TheraAgent yields a +0.43 improvement in therapeutic quality, with low-quality responses improving by +2.45 points and a 94% recovery rate.
-->
[Submitted on 29 Jun 2026]
Title:Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support
View a PDF of the paper titled Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support, by Mizanur Rahman and 6 other authors
View PDF HTML (experimental)
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 this https URL.
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
Cite as: arXiv:2606.30887 [cs.CL]
(or arXiv:2606.30887v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.30887
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Elham Dolatabadi [view email] [v1] Mon, 29 Jun 2026 20:22:25 UTC (6,483 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support, by Mizanur Rahman and 6 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-06
Change to browse by:
cs cs.AI cs.MA
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)