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-agent platforms, what they are and how we see them applied to the enterprise.

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 model and they can then use this knowledge to generate new content that is often indistinguishable from human-created work. Depending on the training dataset, prompt, parameters and the purpose of the model, the results/outcomes will change, and the model may “hallucinate”. For sure you’ve already seen that some of the models behave better than others based on the ask, such as dealing with natural language or generating an image. Experiments say that the use of plugins or agents can greatly improve the outcomes or results for many generic or specific tasks enabling decisions to be made on the most up-to-date information. Examples are the use of ChatGTP functions/plugins to customize a specific behaviour or integration, 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.

Using one agent at a time limits the capabilities of how far we can go, and that’s where the Multi-Agents System (MAS) helps, 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 or even work 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 highlight benefits 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 can assume complex organisational roles through actors (synthesised through agents) to automate collaboration for solving complex tasks. Such capability can produce outstanding business results and drive optimised business outcomes.

Think of multi-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 system.

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

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

A recent paper from Microsoft, Pennsylvania State University and the University of Washington (https://arxiv.org/pdf/2308.08155.pdf), is one example of a multi-agent system. The paper states that by combining multiple agents and focusing on the tasks they are best for, we end up having better outcomes.

It’s important to highlight, that this doesn’t have to be just chaining of LLMs, multiple types of existing or new AI/ML models can be aggregated to address specific goals and tasks, and integration with third-party tools that sometimes can perform extremely well for specific problems.

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.

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

·       Create a collaboration mechanism between agents that results 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 built using multi-agent systems.

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 accurate calculations, 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 able to be specific for the different roles associated with coding. You could see an analogy in the real world, where a developer doing it all, gathering requirements, doing the design, coding and then testing, would not have the best results.

Conversations interactions, where multiple interactions between user and machines are possible, having agents acting as mediators for conflicts, expediting trivial and non-complex or critical judicial processes that could drive to the agreement between parts without the need for complex processes taking a long time to get up to results. Traditional chatbots are very dialogue 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 a high level of automation without such 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 interaction tasks.

Retrieval-augmented Generation is known as a technique that improves the quality of text generated by LLMs by incorporating information from corporate knowledge sources. The text 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 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 adapting to changing business needs and can scale to meet the demands of even the largest enterprises.

·       Improved efficiency and productivity:  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 a 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 responding to customer inquiries more quickly and efficiently considering the different roles that might be required.

·       Improved planning: by creating the entire set of artefacts required for the planning of specific goals, along with an 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, this could mean optimizing supply chains, predicting market trends, or managing large-scale projects.

Examples of use cases where multi-agent systems are already being experimented with

·       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, identify bottlenecks, launch marketing campaigns, and analyze the results to apply improvements along the sales process.

·       Create marketing campaigns for products: where multiple roles and collaborations of humans would be required, and long meetings, for those goods not sold or 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 the importance of minimizing waste and minimize loses. 

·       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-agents 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 have generated a lot of discussion and investment in ethical AI.  Of course, looking at the positive side, 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 multi-agent systems continues 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

Miguel Gaspar, Solution Architect, TSO EMEA Team

Shynish Meladath, Solution Architect, TSO EMEA Team

Should you require more information, please contact any of the authors: miguel.gaspar@hitachids.com, shynish.meladath@hitachids.com or lisbeth.solano@hitachids.com