Hitachi Application Reliability Centers

Multi-agent: the GenAI secret weapon for enterprise success

This thread has been viewed 6 times
  • 1.  Multi-agent: the GenAI secret weapon for enterprise success

    Posted 10-27-2023 09:10

    Multi-agent: the GenAI secret weapon for enterprise success

    Welcome to the first article in an upcoming series on Generative AI at Hitachi.  GenAI is one of the most rapidly developing fields of artificial intelligence and continues to advance at breakneck speed.  In this series of articles, we will be looking into some of the more interesting concepts and use-cases both within Hitachi and the wider world.

    In this first article, we will introduce the reader to multi-agents' platforms, what they are and how and we see them applied to the enterprise in the near future.

    The use of LLMs and some challenges imposed today  

    GenAI models are trained on massive datasets, advanced methodologies, or even on data generated from another models and they can then use this knowledge to generate new content that is often indistinguishable from human-created work. Depending on these parameters and the purpose of the model, the results/outcomes will change, or models may "hallucinate". For sure you've seen that some of models behave better than others based on the ask, per instance dealing with natural language or generating an image. Experiments says, that the use of plugins or agents can greatly improve the outcomes or results for many generic and specific tasks. Such as example is the use of ChatGTP functions/plugins, or as in Retrieval Augmented Generation (RAG, such as Azure Cognitive Search) where LLM models are injected with relevant information before they do their reasoning, enabling decisions to be made on the most up-to-date information.

    Using one agent at a time limits the capabilities of how far we can go, and that's where Multi-Agents System (MAS) help, by allowing interaction between user and agents, both human and synthetic.  Advanced use cases enable agents to generate code and execute the tasks for you, even working collaboratively between themselves. 

    "By 2026, more than 80% of enterprises will have used generative AI APIs and models and/or deployed GenAI-enabled applications in production environments, up from less than 5% in 2023."

     Source: Gartner 2023 (link here)

    Gartner also highlight benefits and for "business users, that will have ubiquitous access to knowledge and technical skills that wasn't possible before, heralding a new wave of productivity". Multi-agents can bring the technical skills that will improve business productivity, so let's discuss how?

    Multi Agent Systems using Generative AI

    Multi-agent systems are capable of assuming complex organisational roles through actors (synthetised through agents) to automate collaboration for solving complex tasks. Such capability can produce outstanding business results and drive optimised business outcomes.

    Think of muti-agent frameworks as being able to harness the power of multiple generative AI models, plugins or agents and tools, where collaborative software entities, assigned with different roles to different models are combined cohesively to build a more intelligent and assertive and system. 

    The image below, shows a way to visualise how multi-agents' systems can be combined, being flexible to perform simple to more complex tasks. We can see agents that interact with end user, LLMs, code generation and code interpreters, safeguards, along with the use of tools that are internal or external to the enterprise. 

    Multi-agent framework, managing the interaction between multiple agents and tools

    Multi-agent framework, managing the interaction between multiple agents and tools

    It's important to realise, that this doesn't have to be just chaining of LLM's, in fact multiple types of AI/ML models can be aggregated to address specific goals and tasks, so considering existing models alongside new models can perform extremally good for specific problems.

    for example, a recent paper from Microsoft, Pennsylvania State University and the University of Washington (https://arxiv.org/pdf/2308.08155.pdf), it is proven that by having multiple agents, combined and focusing on the tasks they are best for, we end up with better outcomes. 

    Here are a few key features of multi-agent systems: 

    ·      Create new types of intelligence that can perform more complex tasks, with greater results.

    ·      Use of LLMs and/or tools to create intelligent agents to communicate and collaborate with each other.

    ·      Generate improved inputs for intelligent agents, which can help them to perform the tasks more effectively.

    ·      Create a collaboration mechanism between agents that result in increased efficiency and better outcomes for the asks made by humans or other applications. 

    Looking at the diagram below, we can see diverse applications that can be build using multi-agent systems.

    Example of applications of Multi-agents systems, and how the agents can collaborate for augmented outcomes

    Example of applications of Multi-agents systems, and how the agents can collaborate for augmented outcomes

    Math solving, where the agents are combined to address questions related to math, where LLMs are usually not good for, however using multiple agents we can indeed perform calculations that are accurate, still providing a very compiling answer.

    Multi agent coding, where agents are being used to generate user-stories, code, tests or even graphical design for software/applications, while a simple agent would not be able to perform all mentioned roles, or not being able to be specific for the different roles associated with coding. You could see an analogy as in real world, where a developer gathering requirements, doing the design, coding and then testing, would not have the best of the results.

    Conversations interactions, where multiple interactions between user and machines is possible having agents acting and mediators for conflicts, expediting trivial and non-complex or critical judicial processes that could drive to agreement between parts without the need for complex processes taking long time to get up to results. Traditional chat bots are very dialog flow oriented while conversational AI will provide a much better experience to the end user besides being able to cover more questions or asks.

    Business process automation, being supported by corporate operational systems, agents will be used to interact with humans or applications in other to achieve high level of automation without such as enhanced customer experience and overcome the challenges imposed by legacy bots.

    Online decision making, where documents, webpages, third-party systems, or even abroad knowledge bases are used to enrich decision making inside the organization. This is an example where web interactions tasks.

    Retrieval-augmented Generation, known already as being technique that improves the quality of text generated by LLMs by incorporating information from corporate knowledge sources. The information is captured before being submitted with the original prompt to LLMs that will originate the final output, where information from inside corporations will still be kept safe and not exposed to outside of the context of the task being performed.

    What are then the benefits that we could expect out of Muti-agent systems and are the first applications at the enterprises?

    Here are some advantages: 

    ·      Increased flexibility and scalability: by easily adapt to changing business needs and can scale to meet the demands of even the largest enterprises.

    ·      Improved efficiency and productivity: by automating many tasks that are currently performed by humans on distinct roles, freeing up employees to focus on more strategic work.

    ·      Enhanced decision-making: Agents can make decisions based on local information, leading to faster and more efficient decision-making process. This is crucial in dynamic business environments where quick responses are necessary.

    ·      Improved customer service: by creating personalized customer experiences and to respond to customer inquiries more quickly and efficiently considering the different roles might be required.

    ·      Improved planning: by creating the entire set of artifacts required for the planned of specific goals, along with optimized plan of resources. 

    ·      Complex problem-solving multi-agent systems excel in solving complex problems that involve a large amount of data and variables. In an enterprise setting, this could mean optimizing supply chains, predicting market trends, or managing large-scale projects. 

    Example of use cases where multi-agent systems are already being experimented: 

    ·      Supply chain management: Where multi-agents can be used to optimize the flow of goods and materials through a supply chain, to predict demand, predict and assign orders, to identify bottlenecks, launch marketing campaigns and analyze the results to apply improvements along the sales process. 

    ·      Create marketing campaigns for products not yet sold: where multiple roles and collaborations of humans would be required, and long meetings, those goods not sold, about to expire, others, could be targeted for campaigns that can be planned and managed, all having human security and safety in mind but also importance of minimizing or even eliminating waste of good. 

    ·      Enhanced Customer Experience: Personalization, agents can analyze customer data and behavior to provide personalized experiences, whether it is in customer support interactions, product recommendations or marketing campaigns. This individualized touch can significantly enhance customer satisfaction and loyalty.

    Challenges and ConcernS

    While multi-agent systems hold great promise as a secret weapon for enterprise success, there are indeed challenges and concerns that need to be carefully considered and addressed. There are also some challenges and concerns associated with the use of multi-agent, because as they can be used to perform more effectively and faster, they could be used to create harmful content, such as fake news, propaganda, sophisticated scamming and cyberattacks which has generated a lot of discussion and investment in ethical AI.  Of course, they can also be used to detect and automatically prevent or minimize the impact of attacks whilst executing a neutralization strategy.

    Addressing these challenges requires a combination of technical expertise, rigorous testing, clear policies and regulations and ongoing monitoring. As the field of muti-agent systems continue to evolve, so will the solutions to these challenges. Enterprises investing in this technology must remain vigilant, adaptable, and committed to ethical and responsible AI practices to unlock the full potential of multi-agent systems for their success.

    Summary

    This post was to introduce the reader to multi agent systems, a complex and revolutionary approach to automation in the workplace which has the potential to provide organisations with huge benefits and whose adoption will continue at pace. In our next post we will dive into aspects that need to be considered when using multi-agents. 

    About the Authors: 

    Lisbeth Ron Solano, Solution Architect, TSO EMEA Team

    Miguel Gaspar, Solution Architect, TSO EMEA Team

    Shynish Meladath, Solution Architect, TSO EMEA Team

    Should you require more information, please contact: miguel.gaspar@hitachivantara.com, lisbeth.solano@hitachivantara.com or shynish.meladath@hitachivantara.com


    #ApplicationModernization

    ------------------------------
    Miguel Gaspar
    Software Architecture Engineer Principal
    Hitachi Vantara
    ------------------------------