@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://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1398/",
    doi = "10.18653/v1/2025.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."
}