From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health

Hugging Face Daily Papers Papers
large-language-models mental-health survey ai-in-healthcare nlp cognitive-agents

Summary

This survey paper reviews the application of large language models in mental health, tracing their evolution from basic pattern recognition tools to sophisticated personalized companions.

The rising global prevalence of mental health conditions, together with longstanding barriers in traditional healthcare, such as limited resources, high cost, stigma, and privacy concerns, has created an urgent need for accessible and scalable support. Large Language Models (LLMs) have emerged as a transformative technology with strong potential to democratize mental health support through advanced natural language understanding and generation. However, the rapidly expanding, fragmented body of work in this area lacks a coherent evolutionary narrative, making it difficult to contextualize current progress and identify future directions. This survey addresses this gap by organizing and analyzing the literature around a central thesis: the role of LLMs in mental health is evolving through three distinct, increasingly sophisticated phases. We trace this trajectory from Phase I, in which LLMs act primarily as passive Information Tools and Pattern Recognizers for assessment; through Phase II, where they function as Empathetic Conversationalists for in-the-moment, stateless interactions; to the current frontier, Phase III, which seeks Longitudinal, Personalized Companions implemented as stateful cognitive agents. To support this framework, we systematically review core technologies, agent architectures (Profile, Memory, Reasoning, and Planning), and the critical infrastructure of datasets and benchmarks, highlighting how their evolution underpins this developmental path. Viewing the field through this developmental lens, we provide a comprehensive synthesis of existing work, an insightful narrative of its trajectory, and a clear roadmap for future innovation in responsible, effective, and human-centered AI for mental healthcare. A curated collection of the resources reviewed in this survey is available at our project repository: https://github.com/Emo-gml/Awesome-Mental-Health-LLMs.
Original Article
View Cached Full Text

Cached at: 09/23/26, 03:31 AM

Paper page - From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health

Source: https://huggingface.co/papers/2609.25186 Published on Sep 21

·

Submitted byhttps://huggingface.co/GMLHUHE

HU HEon Sep 23

Authors:

,

,

,

,

,

,

,

,

,

Abstract

Therisingglobalprevalenceofmentalhealthconditions,togetherwithlongstandingbarriersintraditionalhealthcare,suchaslimitedresources,highcost,stigma,andprivacyconcerns,hascreatedanurgentneedforaccessibleandscalablesupport.LargeLanguageModels(LLMs)haveemergedasatransformativetechnologywithstrongpotentialtodemocratizementalhealthsupportthroughadvancednaturallanguageunderstandingandgeneration.However,therapidlyexpanding,fragmentedbodyofworkinthisarealacksacoherentevolutionarynarrative,makingitdifficulttocontextualizecurrentprogressandidentifyfuturedirections.Thissurveyaddressesthisgapbyorganizingandanalyzingtheliteraturearoundacentralthesis:theroleofLLMsinmentalhealthisevolvingthroughthreedistinct,increasinglysophisticatedphases.WetracethistrajectoryfromPhaseI,inwhichLLMsactprimarilyaspassiveInformationToolsandPatternRecognizersforassessment;throughPhaseII,wheretheyfunctionasEmpatheticConversationalistsforin-the-moment,statelessinteractions;tothecurrentfrontier,PhaseIII,whichseeksLongitudinal,PersonalizedCompanionsimplementedasstatefulcognitiveagents.Tosupportthisframework,wesystematicallyreviewcoretechnologies,agentarchitectures(Profile,Memory,Reasoning,andPlanning),andthecriticalinfrastructureofdatasetsandbenchmarks,highlightinghowtheirevolutionunderpinsthisdevelopmentalpath.Viewingthefieldthroughthisdevelopmentallens,weprovideacomprehensivesynthesisofexistingwork,aninsightfulnarrativeofitstrajectory,andaclearroadmapforfutureinnovationinresponsible,effective,andhuman-centeredAIformentalhealthcare.Acuratedcollectionoftheresourcesreviewedinthissurveyisavailableatourprojectrepository:https://github.com/Emo-gml/Awesome-Mental-Health-LLMs.

View arXiv pageView PDFGitHub126Add to collection

Get this paper in your agent:

hf papers read 2609\.25186

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.25186 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.25186 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.25186 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

LUNAR: Benchmarking Personalized Large Language Models on UNiversal User BehAvioR Logs

arXiv cs.AI

This paper introduces LUNAR, a benchmark for evaluating how large language models personalize responses from longitudinal app interaction histories across daily-life domains such as clothing, food, housing, and mobility. Experiments on 19 mainstream LLMs reveal that effective personalization depends on evidence selection and cross-domain integration, and that stronger personalization can come at the cost of privacy protection.