Multi-agent: A GenAI secret weapon for enterprise success

GenAI is one of the most rapidly developing fields of artificial intelligence and continues to advance at breakneck speed.? In this first article, we will introduce the reader to multi-agent platforms, their importance, 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 data generated from another model. They can then use this knowledge to create new content 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 models behave better than others based on the ask, such as dealing with natural language or generating an image. Experiments say that using plugins or agents can significantly improve the outcomes or results for many generic or specific tasks, enabling decisions based on the most up-to-date information. Examples are ChatGTP functions/plugins to customise a particular 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.

“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 to 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 harnessing the power of multiple generative AI models, plugins, agents, and tools, where collaborative software entities assigned 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 interacting with end users, LLMs, code generation and code interpreters, safeguards, and using internal or external tools in the enterprise.

A recent paper from Microsoft, Pennsylvania State University and the University of Washington, titled "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation", 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 have 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 sometimes can perform exceptionally 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 more significant 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 perform tasks more effectively.
• Create a collaboration mechanism between agents that increases 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.

• Math solving, where the agents are combined to address math-related questions, where LLMs are usually unsuitable; however, we can perform accurate calculations using multiple agents, still providing a very compiling answer.
• Multi-agent coding, where agents are 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 be specific for the different roles associated with coding. You could see an analogy in the real world: a developer doing it all, gathering requirements, doing the design, coding and 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 needing 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, supported by corporate operational systems, will allow agents to interact with humans or applications 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 knowledge bases from abroad enrich decision-making inside the organisation. This is an example of web interaction tasks.
• Retrieval-augmented Generation is 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 data from inside corporations will still be kept safe and not exposed outside of the context of the task being performed.

What benefits could we expect from Muti-agent systems, and are they the first applications at the enterprises?

Here are some advantages:

• Increased flexibility and scalability: It can scale to meet the demands of even the largest enterprises by quickly adapting to changing business needs.
• Improved efficiency and productivity: automating many tasks 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. This is crucial in dynamic business environments where quick responses are necessary.
• Improved customer service: created personalised customer experiences and responded 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 planning specific goals, along with an optimised plan of resources.
• Complex problem-solving multi-agent systems excel in solving complex problems that involve a large amount of data and variables. This could mean optimising supply chains, predicting market trends, or managing large-scale projects in an enterprise.

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

• Supply chain management: Where multi-agents can be used to optimise the flow of goods and materials through a supply chain, to predict demand, predict and assign orders, identify bottlenecks, launch marketing campaigns, and analyse 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 minimising waste and minimise loses.
• Enhanced Customer Experience: Personalization agents can analyse customer data and behaviour to provide personalised experiences, whether in customer support interactions, product recommendations or marketing campaigns. This individualised 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, challenges and concerns need to be carefully considered and addressed. There are also some challenges and considerations 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 minimise the impact of attacks whilst executing a neutralisation strategy.

Addressing these challenges requires 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 introduced the reader to multi-agent systems, a complex and revolutionary approach to automation in the workplace that has the potential to provide organisations with huge benefits and whose adoption will continue at a fast pace.

The article was written by Shynish Meladath , Lisbeth R. , and Miguel Gaspar with the support and review of Mark Stubbs .