The Interplay of Social and Robotics Theories in AGI Alignment: Navigating the Digital city through Simulation-based Multi-Agent Systems
Конференцијски прилог (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
This study delves into the task of aligning Artificial General Intelligence (AGI) and Large Language Models (LLMs) to societal and ethical norms by using theoretical frameworks derived from social science and robotics. The expansive adoption of AGI technologies magnifies the importance of aligning AGI with human values and ethical boundaries. This paper presents an innovative simulation-based approach, engaging autonomous ’digital citizens’ within a multi-agent system simulation in a virtual city environment. The virtual city serves as a platform to examine systematic interactions and decision-making, leveraging various theories, notably, Social Simulation Theory, Theory of Reasoned Action, Multi-Agent System Theory, and Situated Action Theory. The aim of establishing this digital landscape is to create a fluid platform that enables our AI agents to engage in interactions and enact independent decisions, thereby recreating life-like situations. The LLMs, embodying the personas in this ...digital city, operate as the leading agents demonstrating substantial levels of autonomy. Despite the promising advantages of this approach, limitations primarily lie in the unpredictability of real-world social structures. This work aims to promote a deeper understanding of AGI dynamics and contribute to its future development, prioritizing the
integration of diverse societal perspectives in the process.
Кључне речи:
Artificial General Intelligence / Large Language Models / Social Theories / Robotics Theories / Simulation-Based ApproachИзвор:
Proceedings The Fourteenth International Conference on Business Information Security BISEC 2023, 2023, 71-76Издавач:
- Niš : Metropolitan University and Udruženje eSigurnost
Финансирање / пројекти:
- "info:eu-repo/grantAgreement/MESTD/inst-2020/200025/RS//" (RS-MESTD-inst-2020-200025)
Колекције
Институција/група
IFDTTY - CONF AU - Bojić, Ljubiša AU - Đapić, Vladimir PY - 2023 UR - http://rifdt.instifdt.bg.ac.rs/123456789/3781 AB - This study delves into the task of aligning Artificial General Intelligence (AGI) and Large Language Models (LLMs) to societal and ethical norms by using theoretical frameworks derived from social science and robotics. The expansive adoption of AGI technologies magnifies the importance of aligning AGI with human values and ethical boundaries. This paper presents an innovative simulation-based approach, engaging autonomous ’digital citizens’ within a multi-agent system simulation in a virtual city environment. The virtual city serves as a platform to examine systematic interactions and decision-making, leveraging various theories, notably, Social Simulation Theory, Theory of Reasoned Action, Multi-Agent System Theory, and Situated Action Theory. The aim of establishing this digital landscape is to create a fluid platform that enables our AI agents to engage in interactions and enact independent decisions, thereby recreating life-like situations. The LLMs, embodying the personas in this digital city, operate as the leading agents demonstrating substantial levels of autonomy. Despite the promising advantages of this approach, limitations primarily lie in the unpredictability of real-world social structures. This work aims to promote a deeper understanding of AGI dynamics and contribute to its future development, prioritizing the integration of diverse societal perspectives in the process. PB - Niš : Metropolitan University and Udruženje eSigurnost C3 - Proceedings The Fourteenth International Conference on Business Information Security BISEC 2023 T1 - The Interplay of Social and Robotics Theories in AGI Alignment: Navigating the Digital city through Simulation-based Multi-Agent Systems SP - 71 EP - 76 UR - https://hdl.handle.net/21.15107/rcub_rifdt_3781 ER -
@conference{ author = "Bojić, Ljubiša and Đapić, Vladimir", year = "2023", abstract = "This study delves into the task of aligning Artificial General Intelligence (AGI) and Large Language Models (LLMs) to societal and ethical norms by using theoretical frameworks derived from social science and robotics. The expansive adoption of AGI technologies magnifies the importance of aligning AGI with human values and ethical boundaries. This paper presents an innovative simulation-based approach, engaging autonomous ’digital citizens’ within a multi-agent system simulation in a virtual city environment. The virtual city serves as a platform to examine systematic interactions and decision-making, leveraging various theories, notably, Social Simulation Theory, Theory of Reasoned Action, Multi-Agent System Theory, and Situated Action Theory. The aim of establishing this digital landscape is to create a fluid platform that enables our AI agents to engage in interactions and enact independent decisions, thereby recreating life-like situations. The LLMs, embodying the personas in this digital city, operate as the leading agents demonstrating substantial levels of autonomy. Despite the promising advantages of this approach, limitations primarily lie in the unpredictability of real-world social structures. This work aims to promote a deeper understanding of AGI dynamics and contribute to its future development, prioritizing the integration of diverse societal perspectives in the process.", publisher = "Niš : Metropolitan University and Udruženje eSigurnost", journal = "Proceedings The Fourteenth International Conference on Business Information Security BISEC 2023", title = "The Interplay of Social and Robotics Theories in AGI Alignment: Navigating the Digital city through Simulation-based Multi-Agent Systems", pages = "71-76", url = "https://hdl.handle.net/21.15107/rcub_rifdt_3781" }
Bojić, L.,& Đapić, V.. (2023). The Interplay of Social and Robotics Theories in AGI Alignment: Navigating the Digital city through Simulation-based Multi-Agent Systems. in Proceedings The Fourteenth International Conference on Business Information Security BISEC 2023 Niš : Metropolitan University and Udruženje eSigurnost., 71-76. https://hdl.handle.net/21.15107/rcub_rifdt_3781
Bojić L, Đapić V. The Interplay of Social and Robotics Theories in AGI Alignment: Navigating the Digital city through Simulation-based Multi-Agent Systems. in Proceedings The Fourteenth International Conference on Business Information Security BISEC 2023. 2023;:71-76. https://hdl.handle.net/21.15107/rcub_rifdt_3781 .
Bojić, Ljubiša, Đapić, Vladimir, "The Interplay of Social and Robotics Theories in AGI Alignment: Navigating the Digital city through Simulation-based Multi-Agent Systems" in Proceedings The Fourteenth International Conference on Business Information Security BISEC 2023 (2023):71-76, https://hdl.handle.net/21.15107/rcub_rifdt_3781 .