@inproceedings{liu-etal-2026-minduntangler,
title = "{M}ind{U}ntangler: Resolving Cognitive Entanglements via Multi-Agent Topological Routing in Psychological Counseling",
author = "Liu, Xiaoyu and
Diao, Yufeng and
Zeng, Jingjie and
Li, Shiqi and
Zhang, Hao and
Yang, Liang",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1452/",
pages = "30928--30946",
ISBN = "979-8-89176-462-0",
abstract = "While Large Language Models (LLMs) offer scalable mental health support, they typically operate within the superficial text space, providing generic comfort that fails to resolve a patient{'}s deep-rooted cognitive distortions. To address this, we propose **MindUntangler** a novel multi-agent framework that models psychological counseling as a dynamic topological routing task. By conceptualizing cognitive distortions as ``pathological topologies''{---}tangible knots in a patient{'}s Cognitive Topology Graph (CTG){---}our system dynamically tracks and resolves these complex connections through pluralistic therapeutic routing. To ensure clinical safety, we integrate topological guardrails and align the model via a novel topology-driven Direct Preference Optimization. Experiments on two benchmarks demonstrate state-of-the-art performance in cognitive restructuring and clinical efficacy. Ultimately, this work shifts AI therapy from textual empathy to computable, structural interventions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-minduntangler">
<titleInfo>
<title>MindUntangler: Resolving Cognitive Entanglements via Multi-Agent Topological Routing in Psychological Counseling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoyu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufeng</namePart>
<namePart type="family">Diao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingjie</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiqi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>While Large Language Models (LLMs) offer scalable mental health support, they typically operate within the superficial text space, providing generic comfort that fails to resolve a patient’s deep-rooted cognitive distortions. To address this, we propose **MindUntangler** a novel multi-agent framework that models psychological counseling as a dynamic topological routing task. By conceptualizing cognitive distortions as “pathological topologies”—tangible knots in a patient’s Cognitive Topology Graph (CTG)—our system dynamically tracks and resolves these complex connections through pluralistic therapeutic routing. To ensure clinical safety, we integrate topological guardrails and align the model via a novel topology-driven Direct Preference Optimization. Experiments on two benchmarks demonstrate state-of-the-art performance in cognitive restructuring and clinical efficacy. Ultimately, this work shifts AI therapy from textual empathy to computable, structural interventions.</abstract>
<identifier type="citekey">liu-etal-2026-minduntangler</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1452/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>30928</start>
<end>30946</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MindUntangler: Resolving Cognitive Entanglements via Multi-Agent Topological Routing in Psychological Counseling
%A Liu, Xiaoyu
%A Diao, Yufeng
%A Zeng, Jingjie
%A Li, Shiqi
%A Zhang, Hao
%A Yang, Liang
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F liu-etal-2026-minduntangler
%X While Large Language Models (LLMs) offer scalable mental health support, they typically operate within the superficial text space, providing generic comfort that fails to resolve a patient’s deep-rooted cognitive distortions. To address this, we propose **MindUntangler** a novel multi-agent framework that models psychological counseling as a dynamic topological routing task. By conceptualizing cognitive distortions as “pathological topologies”—tangible knots in a patient’s Cognitive Topology Graph (CTG)—our system dynamically tracks and resolves these complex connections through pluralistic therapeutic routing. To ensure clinical safety, we integrate topological guardrails and align the model via a novel topology-driven Direct Preference Optimization. Experiments on two benchmarks demonstrate state-of-the-art performance in cognitive restructuring and clinical efficacy. Ultimately, this work shifts AI therapy from textual empathy to computable, structural interventions.
%U https://aclanthology.org/2026.findings-emnlp.1452/
%P 30928-30946
Markdown (Informal)
[MindUntangler: Resolving Cognitive Entanglements via Multi-Agent Topological Routing in Psychological Counseling](https://aclanthology.org/2026.findings-emnlp.1452/) (Liu et al., Findings 2026)
ACL