Social Life Simulation for Non-Cognitive Skills Learning

TL;DR

SimuLife++ introduces an LLM-driven narrative platform designed to cultivate non-cognitive skills through protagonist-centered stories augmented by a Sage Agent, a bystander mentor that prompts just-in-time reflection. A within-subject study with 18 participants shows the Sage Agent can increase narrative immersion and enhance reflection on motivation, self-perceptions, and resilience, while group chats amplify user engagement. Qualitative analyses reveal the Sage Agent serves multiple roles (mentor, bystander, companion, assessor) and highlight design opportunities and challenges in multi-agent interactions, realism of AI characters, and ethical considerations. The work provides empirical evidence and actionable design implications for applying generative AI to narrative solutions that develop social and emotional competencies, with potential extensions to richer agents, real-life conflict scenarios, and multiplayer settings. Overall, SimuLife++ demonstrates the viability of AI-assisted narrative learning to promote non-cognitive skills, underscoring the importance of context-aware mentoring and user control in scalable social-skill development.

Abstract

Non-cognitive skills are crucial for personal and social life well-being, and such skill development can be supported by narrative-based (e.g., storytelling) technologies. While generative AI enables interactive and role-playing storytelling, little is known about how users engage with and perceive the use of AI in social life simulation for non-cognitive skills learning. Additionally, the benefits of AI mentorship on self-reflection awareness and ability in this context remain largely underexplored. To this end, we introduced Simulife++, an interactive platform enabled by a large language model (LLM). The system allows users to act as protagonists, creating stories with one or multiple AI-based characters in diverse social scenarios. In particular, we expanded the Human-AI interaction to a Human-AI-AI collaboration by including a Sage Agent, who acts as a bystander, providing users with some perspectives and guidance on their choices and conversations in terms of non-cognitive skills to promote reflection. In a within-subject user study, our quantitative results reveal that, when accompanied by Sage Agent, users exhibit significantly higher levels of reflection on motivation, self-perceptions, and resilience & coping, along with an enhanced experience of narrative transportation. Additionally, our qualitative findings suggest that Sage Agent plays a crucial role in promoting reflection on non-cognitive skills, enhancing social communication and decision-making performance, and improving overall user experience within Simulife++. Multiple supportive relationships between Sage Agent and users were also reported. We offer design implications for the application of generative AI in narrative solutions and the future potential of Sage Agent for non-cognitive skill development in broader social contexts.

Figures (4)

• Figure 1: The interfaces of SimuLife++ includes: (a) a login page requiring email, password, and agreement to policies and terms; (b) a home page displaying scripts for users to choose from and their history of script-play collections; (c) a script description page listing information about the story, including its name, original author, description, and main characters; (d) a decision-making page involving an event where users can choose one of three options; (e) an individual chat page primarily featuring a chat event with one character, where the left side shows the story and the right side displays the conversation panel; (f) a social media check page consisting of the social media post information for the character involved in the individual chat; (g) a group chat page displaying a group chat event from the story, with the story on the left and the conversation panel on the right; (h) a character background page enabling users to check background information and persona for each character encountered in the story.
• Figure 2: Comparative Analysis of Non-cognitive Skill Scale and Narrative Transportation Scale. (a) A radar chart illustrating the differences in non-cognitive skills between groups with and without the Sage Agent intervention. Skills assessed include resilience & coping, social competencies, metacognitive strategies, self-control, motivation, perseverance, and self-perceptions. (b) A bar graph showing responses to narrative transportation scale questions, with orange bars representing the "with Sage Agent" group and blue bars representing the "without Sage Agent" group. Error bars indicate standard deviation, and p-values are provided to show statistical significance.
• Figure 3: Box plots of communication metrics in conversations with a Sage Agent versus without a Sage Agent in the top panel line and individual chats versus group chat in the bottom panel. Note that the term "message" in this context refers to the input provided by the user to the AI in conversations, and does not include the output generated by the AI in response. Message length is the total length of user messages of all conversations during the time, word count refers to the total number of words, and message count refers to the number of messages.
• Figure 4: Comparative Analysis of generated story with and without a Sage Agent. (a) The line graphs illustrate the average scores across three categories - Staging, Plot Progression, and Cognitive Tension - comparing scenarios with and without the use of a Sage Agent. (b) A radar chart summarizing the overall and individual category effects.