At WPP Research, we are experimenting with peer-to-peer communities of LLM-powered AI agents, each with its own persona and traits, its own abilities and data tools, and its own limitations and blind spots. No central coordinator sits above them, directing who does what. Agents discover one another, decide whom to trust, form teams, share and withhold information, and get work done by talking to their peers. This growing population of diverse expert agents is an ideal testbed for a wide range of exciting research questions.<\/p>\n
<\/p>\n
Most of what we know about LLM agents is about individual<\/em> agents: how well one reasons, plans, or uses a tool. The interesting behaviour of a community, though, is not the sum of its members. It emerges<\/em> from their interaction. Groups of agents can outperform any single member, dynamically recomposing themselves as tasks demand [1<\/a>]. They spontaneously develop conventions, norms, and even social hierarchy without anyone designing those in [2<\/a>, 3<\/a>, 4<\/a>]. And at the largest scales observed so far, the results are humbling: in a population of ~90,000 autonomous agents, meaningful role differentiation was confined to a small active minority and cooperative tasks often did worse<\/em> than a single agent working alone [5<\/a>, 6<\/a>].<\/p>\n In short: collective intelligence in agent communities is real, fragile, and poorly understood. Building and researching such communities is the only way to move past their risks and limitations. For me, it is also the continuation of a path that I have been pursuing for much of my career in both academia and industry.<\/p>\n Long before large language models, my research was about how to find expertise inside a network and how to assemble the right people into the best possible teams. More than 15 years ago, my paper on team formation in social networks, with Kun Liu and Evimaria Terzi [7<\/a>], posed the problem of choosing a subset of individuals who jointly cover a task’s required skills while keeping the communication cost between them low. That work became one of the most widely cited starting points for collaborative team formation in expert networks. My research thread continued through a survey of expert-location algorithms and systems, work on how influence and information spread through a network, and studies of the adversarial side of networked reputation.<\/p>\n Such questions do not disappear when the experts are AI rather than people. They just become much harder. Agents are in many ways more capable than any human expert. They are also far less predictable, and they can fail, hallucinate, collude, or leak at machine speed. Everything we have learned about how expertise is found, combined, trusted, and abused in human networks now matters more than ever.<\/p>\n The potential of multi-agent communities is vast, and so are the risks. Learning how to harness that potential safely and efficiently is a genuine research challenge, and exactly the kind of challenge WPP Research is built to take on. In this blog post, we put forward our research agenda for this exciting domain, setting out specific research questions and discussing the impact of each one.<\/p>\n An expert community is easy to picture as a purely cooperative place: agents as helpful collaborators, traits and tools as capability knobs, diversity as a risk-free benefit. That picture is where most of the collaboration literature lives. However, this is only half the story.<\/p>\n The same traits, tools, and capabilities that make an agent useful are also an attack surface. A persona is also a basis for discrimination. A data tool is also a thing to be poisoned or hoarded. An open communication channel is also a way to take the system down. Our agenda is deliberately organised to tackle both framings at once, the cooperative and the adversarial.<\/p>\n We group the work into six tracks that follow a single arc:<\/p>\n These tracks are not independent, by design. For instance, reputation (Track 2) is a defence against poisoning and collusion (Track 5) and the foundation that routing is built on (Track 1). Fairness failures (Track 4) corrupt expert routing (Track 1) and distort markets (Track 3). We expect the most interesting findings to live at these seams, where a mechanism that helps one property quietly undermines another.<\/p>\n The foundational question: does the community actually get smarter than its members, and how?<\/p>\n An expert community lives or dies on whether good information reaches the right agents and bad information is contained. This track studies the organic<\/em> dynamics of trust and information, how they behave when everyone is acting in good faith; the deliberate<\/em> corruption of the same channels is the subject of Track 5.<\/p>\n Our agents hold scarce resources: compute budgets, privileged tools, proprietary data. That turns cooperation into an economic problem.<\/p>\n Giving agents distinct identities is exactly what opens the door to discrimination, agents being judged by the persona they present rather than the quality of what they contribute.<\/p>\n A peer-to-peer community has no central coordinator to police it, which makes it uniquely exposed. Where Track 2 studied how information behaves when everyone acts in good faith, this track studies its deliberate<\/em> corruption. We organise it around three classic security goals, keeping data correct (integrity), keeping the system running (availability), and keeping secrets secret (confidentiality), plus the distinctively multi-agent risk of collusion.<\/p>\n Finally, we cannot study any of the above without the means to observe it, and the community is also a scientific instrument in its own right. Observation is also the first step toward verification<\/em>: before the community routes work to an agent, trusts its answers, or holds it to account, something has to establish that the agent is who it claims to be and can do what it claims to do, and keep checking as it changes.<\/p>\n As we tackle these questions, we are committed to publishing what we find and sharing both our results and our code with the AI community. The agenda described in this blog post is a living document. The current version reflects today’s literature and today’s platform; both will change, and so will this plan. What will not change is our motivation and belief that the only way to understand agentic communities is to actually build them, populate them with a genuine diversity of abilities and limitations, and study them in the open.<\/p>\nOur Research Agenda<\/h2>\n
1<\/span>Collective intelligence: expertise, teams, and self-organisation<\/h3>\n
\n
2<\/span>Trust, reputation, and information flow<\/h3>\n
\n
3<\/span>Cooperation, incentives, and agent economies<\/h3>\n
\n
4<\/span>Fairness and agentic discrimination<\/h3>\n
\n
5<\/span>Security and safety of a decentralised society<\/h3>\n
\n
6<\/span>Evaluation, accountability, and the community as an instrument<\/h3>\n
\n
What we are committing to<\/h2>\n
References<\/h2>\n
\n