Human-AI and Human-Robot Collaboration in the Age of Generative AI, Agentic AI, and Artificial General Intelligence: Opportunities and Challenges

The advancement of Artificial Intelligence (AI) has been exponential, especially in the past few years [1]. Most, if not all, of the AI systems we encounter and are exposed to at this point are Artificial Narrow Intelligence (ANI). ANI specializes in one area and solves problems in one area. Generative AI (GenAI) and Agentic AI (i.e., independent AI agent), at the current stage of development, are regarded as ANI. The race is currently on to develop Artificial General Intelligence (AGI). AGI refers to AI systems as smart as humans across a wide range of cognitive tasks. Recently, OpenAI’s o3 system received a score of 85% from the ARC-AGI benchmark. This score is on par with the average human score. Some argue that OpenAi’s o3 can be regarded as a limited or pioneer version of AGI. After AGI, we will likely enter the age of Artificial Super Intelligence (ASI). ASI operates beyond human-level intelligence and is much smarter than humans in practically every field. In this article, we look at the co-working of humans and AI machines, which is also termed Industry 5.0. What are the opportunities and challenges of Human-AI and Human-Robot collaboration?

Human-Ai and human-robot collaboration can bring about many opportunities. Below are some of them
A. Improved efficiency: AI can process data and information faster than humans and AI systems can operate 24/7. This is especially true for repetitive tasks and tasks that require time-consuming data processing. Further, robots can operate in dark factories or light-out manufacturing environments. With Human-AI and Human-Robot collaboration, humans can focus on more complex cognitive and creative tasks and AI systems (at least for ANI) can operate on those structured and routine tasks. With GenAI, AI machines are breaking into the creativity arena that once was the priced characteristic of humans. AGI will perform at the level of human intelligence, but much faster and more efficiently.
B. Enhanced decision-making and problem-solving quality: With computational speed and power, AI can analyze large quantities of data, identify patterns and trends, and run simulations to test different scenarios to provide human decision-makers with the latest information and insights. The roles of humans and AI/robots in Human-AI and Human-Robot collaboration will evolve with the advancement of AI and AI-powered robots. Agentic AI is now able to make independent decisions and solve problems.
C. Individualization and personalization: AI can capture and analyze individual preferences and contexts (e.g., facial and emotion recognition to identify the human’s mood at the time of engagement) to provide a personalized and situationalaware experience. In the context of learning, AI can create customized content to benefit individual student needs [2]. In the context of healthcare, medical assistant robots can support doctors and nurses in providing better quality healthcare. AI-enabled care companion robots can offer companionship to elderly and lonely adults, which is important as many countries are experiencing an aging population.
D. Scalability and continuity: AI can scale up by adding more hardware (e.g., GPUs) to handle more and more tasks and using more advanced hardware to enhance processing speed. The AI systems can also become smarter with better designs and more training data. For example, ChatGPT has evolved quickly, and its performance enhanced rapidly from ChatGPT 1 in 2018 to ChatGPT 4o in 2024. Further, unlike humans who have a life span of several decades, AI and robots can continuously learn and improve. Thus, many scientists expect AGI to appear eventually, if not in the next few years or already.

The rapid and exponential improvements of AI also pose many challenges. Below are a few of them
A. Bias, fairness, and transparency: Bias, fairness, and transparency are some of the main challenges of AI. The training data for AI may contain biases that will affect the performance of AI systems. The automatic learning and evolution of AI poses further challenges as we may not know what the AI has learned and how it has evolved. With Human-AI and Human-Robot collaboration, AI systems will also learn from humans and will evolve over time, which is a potential risk. If AI systems start to access the Internet, they will learn from the materials and contents on the Internet, which is another risk. The decision-making capabilities of agentic AI may lack transparency. AGI and ASI may operate at a level beyond the comprehension of humans and the lack of transparency is a major concern.
B. Trust and adoption: Trust is central to Human-AI and Human-Robot collaboration. Users need to be able to trust the reliability and accuracy of AI or AI-powered robots to adopt them. For Human-AI and Human-Robot collaboration, the issue of the uncanny valley should be considered. Uncanny valley refers to the uncomfortable sensation one feels when one encounters a robot or virtual character that looks “almost but not quite human.” The uncanny valley is a term that was coined in 1970 by Masahiro Mori [3], a robotics professor at the Tokyo Institute of Technology. The concept of uncanny valley may be evolving as more and more humans are exposed to humanoid robots and the humanoid robots are now more “human-like.”
C. Ethics, privacy, security, and future of work and humanity: Ethical considerations are important for Human-AI and Human-Robot collaborations. Data privacy and security are parts of the ethical considerations [4]. This is especially true for sensitive data, such as healthcare and personal financial data [5]. Similarly, the future of work and humanity are important ethical considerations. Is it ethical to continue to develop AI technology, such as AGI, that results in the displacement and/or elimination of jobs for humans and may threaten the survival of humanity in the future? Developing and underdeveloped countries typically use manufacturing to develop and grow their economies [6]. China has been very successful in this aspect and is known as the world’s factory. With AI, especially with advanced AI systems such as agentic AI and AGI, manufacturing may become more and more automated and involve human labor less and less. Many developing and underdeveloped countries may not be able to further their economic development using manufacturing. Further, even whitecollar jobs may soon be “AI-Ifying” with many white-collar jobs supplemented or augmented by AI copilots and AI agents. A future where most humans are relying on Universal Basic Income may not be a future that many humans would like to have.
D. AI in geopolitics: One of the most common Human-AI and Human-Robot collaborations is in the military area and that is an area that is of concern to many scholars who think that the development of AI should not be used to harm other humans. This presents a huge challenge and threat to humanity. Further, nations could see their influence and power rise or fall depending on their investment and development of AI and how they leverage AI for security, intelligence, and economic advantage.

AI will have a major impact on society [7]. Currently, education institutions and policymakers need to understand the immediate and future impact of AI and robots [8]. Some argue that “AI won’t replace Humans-But Humans with AI will replace Humans without AI.” That is true currently and in the near future. Humans must find ways to work with AI to complement humans’ weaknesses and shortcomings (e.g., computational speed). As AI and robotics technologies advance, humans must find ways to work with AI to complement AI and robots’ weaknesses and limitations. With GenAI, agentic AI, and AGI, AI and AI-powered robots will be able to take over more and more tasks and decision-making processes done by humans. Education institutions need to prepare their students for an AI-age and provide continuous learning, reskilling, and retooling. Policymakers need to formulate regulations and policies to prepare humans for the AI age and AI transformation. Resistance is futile![9].

1. Zhang Y, Siau K (2024) Meta-entrepreneurship: An analysis theory on integrating generative AI, agentic AI, and metaverse for entrepreneurship. Journal of Global Information Management 32(1): 1-21.
2. Siau K (2018) Education in the age of artificial intelligence: How will technology shape learning? The Global Analyst 7(3): 22-24.
3. Mori M, Dorman KFM, Kageki N (2012) The uncanny valley. IEEE Robotics and Automation 19(2): 98-100.
4. Yang Y, Siau K, Xie W, Sun Y (2022) Smart health: Intelligent healthcare systems in the metaverse, artificial intelligence, and data science era. Journal of Organizational and End User Computing 34 (1): 1-14.
5. Siau K, Wang W (2020) Artificial intelligence (AI) ethics: ethics of AI and ethical AI. Journal of Database Management 31(2): 74-87.
6. Lautier M (2024) Manufacturing still matters for developing countries. Structural Change and Economic Dynamics 70: 168-177.
7. Qian Y, Siau KL, Nah FF (2024) Societal impacts of artificial intelligence: Ethics, legal, and governance issues. Societal Impacts 3: 100040.
8. Huo X, Siau KL (2024) Generative artificial intelligence in business higher education: A focus group study. Journal of Global Information Management 32(1): 1-21.
9. Wang W, Siau K (2019) Artificial intelligence, machine learning, automation, robotics, future of work and future of humanity: A review and research agenda. Journal of Database Management 30(1): 61-79.