We propose a computational multi-agent society experiment framework that integrates generative agent-based modeling with virtual ethnographic methods to investigate how group stance differentiation and social boundary formation emerge in human–Agent hybrid societies. Across three studies, we find that agents exhibit endogenous stances, independent of their preset identities, and display distinct tonal preferences and response patterns to different discourse strategies. Furthermore, through language interaction, agents actively dismantle existing identity-based power structures and reconstruct self-organized community boundaries based on these stances. Our findings suggest that preset identities do not rigidly determine the agents’ social structures.

    Generative agents have demonstrated impressive capabilities in specific tasks, but most of these frameworks focus on independent tasks and lack attention to social interactions. We introduce a generative agent architecture called ITCMA-S, which includes a basic framework for individual agents and a framework called LTRHA that supports social interactions among multi-agents. This architecture enables agents to identify and filter out behaviors that are detrimental to social interactions, guiding them to choose more favorable actions. We designed a sandbox environment to simulate the natural evolution of social relationships among multiple identity-less agents for experimental evaluation. The results showed that ITCMA-S performed well on multiple evaluation indicators, demonstrating its ability to actively explore the environment, recognize new agents, and acquire new information through continuous actions and dialogue. Observations show that as agents establish connections with each other, they spontaneously form cliques with internal hierarchies around a selected leader and organize collective activities.

    Large Language Models (LLMs) still face challenges in tasks requiring understanding implicit instructions and applying common-sense knowledge. In such scenarios, LLMs may require multiple attempts to achieve human-level performance, potentially leading to inaccurate responses or inferences in practical environments, affecting their long-term consistency and behavior. This paper introduces the Internal Time-Consciousness Machine (ITCM), a computational consciousness structure. We further propose the ITCM-based Agent (ITCMA), which supports behavior generation and reasoning in open-world settings. ITCMA enhances LLMs' ability to understand implicit instructions and apply common-sense knowledge by considering agents' interaction and reasoning with the environment. Evaluations in the Alfworld environment show that trained ITCMA outperforms the state-of-the-art (SOTA) by 9% on the seen set. Even untrained ITCMA achieves a 96% task completion rate on the seen set, 5% higher than SOTA, indicating its superiority over traditional intelligent agents in utility and generalization. In real-world tasks with quadruped robots, the untrained ITCMA achieves an 85% task completion rate, which is close to its performance in the unseen set, demonstrating its comparable utility in real-world settings.

    Interactions between human beings and digital humans have become a new network phenomenon, and these relationships have gradually become a topic of research. There is still a lack of sufficient research on whether and what kind of attachment relationship exists in these situations. Based on this problem, in this study, a digital human was designed that was oriented to social software and put into chat groups for interaction and research. A questionnaire survey, case analysis, and netnography analysis were used to collect and examine relevant data. The study found a correlation between the type of attachment of users and the degree of attachment to the digital human. In addition, users who were heavily dependent on the network were more likely to try to complete their attachment with the digital human. Attachment with the digital human was able to calm the users’ emotional intensity. This attachment was considered as close to a skewed desire projection. Through the intermediary of a digital human, Internet users have been better able to fulfill some of their own desires.

    Conversational artificial intelligence can already independently engage in brief conversations with clients with psychological problems and provide evidence-based psychological interventions. The main objective of this study is to improve the effectiveness and credibility of the large language model in psychological intervention by creating a specialized agent, the VCounselor, to address the limitations observed in popular large language models such as ChatGPT in domain applications. We achieved this goal by proposing a new affective interaction structure and knowledge-enhancement structure. In order to evaluate VCounselor, this study compared the general large language model, the fine-tuned large language model, and VCounselor's knowledge-enhanced large language model. At the same time, the general large language model and the fine-tuned large language model will also be provided with an avatar to compare them as an agent with VCounselor. The comparison results indicated that the affective interaction structure and knowledge-enhancement structure of VCounselor significantly improved the effectiveness and credibility of the psychological intervention, and VCounselor significantly provided positive tendencies for clients' emotions. The conclusion of this study strongly supports that VConselor has a significant advantage in providing psychological support to clients by being able to analyze the patient's problems with relative accuracy and provide professional-level advice that enhances support for clients.

    Taking the influence of various factors on the teaching effect of moral and social courses of primary school students as the research content, a unified examination was conducted on third-grade students from 413 primary schools in Kunming, and 1270 valid questionnaires were obtained from their teachers. A questionnaire for teachers was innovatively designed with 52 dimensions, and the data were analyzed using the SPSS big data analysis platform to find the most influential factors in the teaching and learning of moral and social courses and to propose suggestions for improving the teaching effectiveness of moral and social courses.