@inproceedings{sarangi-etal-2025-agentic,
title = "Agentic-{T}o{M}: Cognition-Inspired Agentic Processing For Enhancing Theory of Mind Reasoning",
author = "Sarangi, Sneheel and
Talele, Chetan and
Salam, Hanan",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.1398/",
pages = "25645--25661",
ISBN = "979-8-89176-335-7",
abstract = "The capacity to attribute mental states like beliefs, desires, and intentions to oneself and others, known as Theory of Mind (ToM), is fundamental to human social intelligence. As Large Language Models (LLMs) are increasingly integrated into complex interactive systems, developing their ToM capabilities is crucial. Such capabilities enable LLMs to understand and predict human behavior, leading to more intuitive and productive interactions. However, current models often struggle with sophisticated reasoning about others' perspectives. In this work, we propose ``Agentic-ToM'', showing that guiding LLMs by embedding psychologically-grounded functions for capabilities such as `perspective taking' and mental state tracking markedly improves their proficiency in ToM tasks. We evaluate the approach on three diverse ToM datasets and show that this method significantly outperforms baselines across all tasks without requiring task-specific modifications."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sarangi-etal-2025-agentic">
<titleInfo>
<title>Agentic-ToM: Cognition-Inspired Agentic Processing For Enhancing Theory of Mind Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sneheel</namePart>
<namePart type="family">Sarangi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chetan</namePart>
<namePart type="family">Talele</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanan</namePart>
<namePart type="family">Salam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>The capacity to attribute mental states like beliefs, desires, and intentions to oneself and others, known as Theory of Mind (ToM), is fundamental to human social intelligence. As Large Language Models (LLMs) are increasingly integrated into complex interactive systems, developing their ToM capabilities is crucial. Such capabilities enable LLMs to understand and predict human behavior, leading to more intuitive and productive interactions. However, current models often struggle with sophisticated reasoning about others’ perspectives. In this work, we propose “Agentic-ToM”, showing that guiding LLMs by embedding psychologically-grounded functions for capabilities such as ‘perspective taking’ and mental state tracking markedly improves their proficiency in ToM tasks. We evaluate the approach on three diverse ToM datasets and show that this method significantly outperforms baselines across all tasks without requiring task-specific modifications.</abstract>
<identifier type="citekey">sarangi-etal-2025-agentic</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.1398/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>25645</start>
<end>25661</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Agentic-ToM: Cognition-Inspired Agentic Processing For Enhancing Theory of Mind Reasoning
%A Sarangi, Sneheel
%A Talele, Chetan
%A Salam, Hanan
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F sarangi-etal-2025-agentic
%X The capacity to attribute mental states like beliefs, desires, and intentions to oneself and others, known as Theory of Mind (ToM), is fundamental to human social intelligence. As Large Language Models (LLMs) are increasingly integrated into complex interactive systems, developing their ToM capabilities is crucial. Such capabilities enable LLMs to understand and predict human behavior, leading to more intuitive and productive interactions. However, current models often struggle with sophisticated reasoning about others’ perspectives. In this work, we propose “Agentic-ToM”, showing that guiding LLMs by embedding psychologically-grounded functions for capabilities such as ‘perspective taking’ and mental state tracking markedly improves their proficiency in ToM tasks. We evaluate the approach on three diverse ToM datasets and show that this method significantly outperforms baselines across all tasks without requiring task-specific modifications.
%U https://aclanthology.org/2025.findings-emnlp.1398/
%P 25645-25661
Markdown (Informal)
[Agentic-ToM: Cognition-Inspired Agentic Processing For Enhancing Theory of Mind Reasoning](https://aclanthology.org/2025.findings-emnlp.1398/) (Sarangi et al., Findings 2025)
ACL