Infusing Theory of Mind into Socially Intelligent LLM Agents

• URL: http://arxiv.org/abs/2509.22887v1
• Date: Fri, 26 Sep 2025 20:07:34 GMT
• Title: Infusing Theory of Mind into Socially Intelligent LLM Agents
• Authors: EunJeong Hwang, Yuwei Yin, Giuseppe Carenini, Peter West, Vered Shwartz,
• Abstract summary: Theory of Mind (ToM) is a key aspect of human social intelligence.<n>We show that social agents that explicitly use ToM get better at dialogue, achieving goals more effectively.<n>We introduce ToMAgent (ToMA), a ToM-focused dialogue agent.
• Score: 31.88529787413754
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Theory of Mind (ToM)-an understanding of the mental states of others-is a key aspect of human social intelligence, yet, chatbots and LLM-based social agents do not typically integrate it. In this work, we demonstrate that LLMs that explicitly use ToM get better at dialogue, achieving goals more effectively. After showing that simply prompting models to generate mental states between dialogue turns already provides significant benefit, we further introduce ToMAgent (ToMA), a ToM-focused dialogue agent. ToMA is trained by pairing ToM with dialogue lookahead to produce mental states that are maximally useful for achieving dialogue goals. Experiments on the Sotopia interactive social evaluation benchmark demonstrate the effectiveness of our method over a range of baselines. Comprehensive analysis shows that ToMA exhibits more strategic, goal-oriented reasoning behaviors, which enable long-horizon adaptation, while maintaining better relationships with their partners. Our results suggest a step forward in integrating ToM for building socially intelligent LLM agents.

Related papers

• GameTalk: Training LLMs for Strategic Conversation [51.29670609281524]
  We introduce textbfGameTalk, a framework for training LLMs to make strategic decisions via multi-turn interactions.<n>Unlike prior work that focuses on single-turn objectives or static action prediction, we train LLMs to optimize a global objective across full conversations.<n>We evaluate this approach on a suite of increasingly complex games, designed to stress different aspects of reasoning, coordination, and opponent modeling.
  arXiv  Detail & Related papers  (2026-01-22T19:18:39Z)
• RecToM: A Benchmark for Evaluating Machine Theory of Mind in LLM-based Conversational Recommender Systems [23.229692182223157]
  We propose RecToM, a novel benchmark for evaluating Large Language models.<n> RecToM focuses on two complementary dimensions: Cognitive Inference and Behavioral Prediction.<n>Extensive experiments on state-of-the-art LLMs demonstrate that RecToM poses a significant challenge.
  arXiv  Detail & Related papers  (2025-11-27T09:58:29Z)
• MOMENTS: A Comprehensive Multimodal Benchmark for Theory of Mind [41.188841829937466]
  MoMentS (Multimodal Mental States) is a benchmark for building socially intelligent multimodal agents.<n>MoMentS includes over 2,300 multiple-choice questions spanning seven distinct ToM categories.<n>We evaluate several MLLMs and find that although vision generally improves performance, models still struggle to integrate it effectively.
  arXiv  Detail & Related papers  (2025-07-06T15:06:30Z)
• SocialEval: Evaluating Social Intelligence of Large Language Models [70.90981021629021]
  Social Intelligence (SI) equips humans with interpersonal abilities to behave wisely in navigating social interactions to achieve social goals.<n>This presents an operational evaluation paradigm: outcome-oriented goal achievement evaluation and process-oriented interpersonal ability evaluation.<n>We propose SocialEval, a script-based bilingual SI benchmark, integrating outcome- and process-oriented evaluation by manually crafting narrative scripts.
  arXiv  Detail & Related papers  (2025-06-01T08:36:51Z)
• MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems [20.58639538648743]
  We introduce MetaMind, a multi-agent framework inspired by psychological theories of metacognition.<n>Our framework achieves state-of-the-art performance across three challenging benchmarks, with 35.7% improvement in real-world social scenarios.<n>This work advances AI systems toward human-like social intelligence, with applications in empathetic dialogue and culturally sensitive interactions.
  arXiv  Detail & Related papers  (2025-05-25T02:32:57Z)
• PersuasiveToM: A Benchmark for Evaluating Machine Theory of Mind in Persuasive Dialogues [27.231701486961917]
  We propose PersuasiveToM, a benchmark designed to evaluate the Theory of Mind abilities of Large Language Models.<n>Our framework contains two core tasks: ToM Reasoning and ToM Application.<n>Our aim with PersuasiveToM is to allow an effective evaluation of the ToM reasoning ability of LLMs with more focus on complex psychological activities.
  arXiv  Detail & Related papers  (2025-02-28T13:04:04Z)
• Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection [31.38516078163367]
  ToM-agent is designed to empower LLMs-based generative agents to simulate ToM in open-domain conversational interactions.<n>ToM-agent disentangles the confidence from mental states, facilitating the emulation of an agent's perception of its counterpart's mental states.<n>Our findings indicate that the ToM-agent can grasp the underlying reasons for their counterpart's behaviors beyond mere semantic-emotional supporting or decision-making based on common sense.
  arXiv  Detail & Related papers  (2025-01-26T00:32:38Z)
• Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations [58.65755268815283]
  Many real dialogues are interactive, meaning an agent's utterances will influence their conversational partner, elicit information, or change their opinion. We use this fact to rewrite and augment existing suboptimal data, and train via offline reinforcement learning (RL) an agent that outperforms both prompting and learning from unaltered human demonstrations. Our results in a user study with real humans show that our approach greatly outperforms existing state-of-the-art dialogue agents.
  arXiv  Detail & Related papers  (2024-11-07T21:37:51Z)
• SOTOPIA-$π$: Interactive Learning of Socially Intelligent Language Agents [73.35393511272791]
  We propose an interactive learning method, SOTOPIA-$pi$, improving the social intelligence of language agents. This method leverages behavior cloning and self-reinforcement training on filtered social interaction data according to large language model (LLM) ratings.
  arXiv  Detail & Related papers  (2024-03-13T17:17:48Z)
• Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations [70.7884839812069]
  Large language models (LLMs) have emerged as powerful and general solutions to many natural language tasks. However, many of the most important applications of language generation are interactive, where an agent has to talk to a person to reach a desired outcome. In this work, we explore a new method for adapting LLMs with RL for such goal-directed dialogue.
  arXiv  Detail & Related papers  (2023-11-09T18:45:16Z)
• Building Emotional Support Chatbots in the Era of LLMs [64.06811786616471]
  We introduce an innovative methodology that synthesizes human insights with the computational prowess of Large Language Models (LLMs) By utilizing the in-context learning potential of ChatGPT, we generate an ExTensible Emotional Support dialogue dataset, named ExTES. Following this, we deploy advanced tuning techniques on the LLaMA model, examining the impact of diverse training strategies, ultimately yielding an LLM meticulously optimized for emotional support interactions.
  arXiv  Detail & Related papers  (2023-08-17T10:49:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.