Related papers: Inefficiencies of Meta Agents for Agent Design
Researchers are investing substantial effort in developing powerful general-purpose agents, wherein Foundation Models are used as modules within agentic systems (e.g. Chain-of-Thought, Self-Reflection, Toolformer). However, the history of…
Using multiple agents was found to improve the debugging capabilities of Large Language Models. However, increasing the number of LLM-agents has several drawbacks such as increasing the running costs and rising the risk for the agents to…
Critical sectors of human society are progressing toward the adoption of powerful artificial intelligence (AI) agents, which are trained individually on behalf of self-interested principals but deployed in a shared environment. Short of…
The remarkable capabilities of Large Language Model (LLM)-driven agents have enabled sophisticated systems to tackle complex, multi-step tasks, but their escalating costs threaten scalability and accessibility. This work presents the first…
Recent developments in sequential experimental design look to construct a policy that can efficiently navigate the design space, in a way that maximises the expected information gain. Whilst there is work on achieving tractable policies for…
Automatic multi-agent systems aim to instantiate agent workflows without relying on manually designed or fixed orchestration. However, existing automatic MAS approaches remain only partially adaptive: they either perform training-free…
Multi-agent systems (MAS), composed of networks of two or more autonomous AI agents, have become increasingly popular in production deployments, yet introduce security risks that do not arise in single-agent settings. Even if individual…
As AI agents evolve, the community is rapidly shifting from single Large Language Models (LLMs) to Multi-Agent Systems (MAS) to overcome cognitive bottlenecks in automated research. However, the optimal multi-agent coordination framework…
The statelessness of foundation models bottlenecks agentic systems' ability to continually learn, a core capability for long-horizon reasoning and adaptation. To address this limitation, agentic systems commonly incorporate memory modules…
People frequently face challenging decision-making problems in which outcomes are uncertain or unknown. Artificial intelligence (AI) algorithms exist that can outperform humans at learning such tasks. Thus, there is an opportunity for AI…
Co-designing autonomous robotic agents involves simultaneously optimizing the controller and physical design of the agent. Its inherent bi-level optimization formulation necessitates an outer loop design optimization driven by an inner loop…
Deploying agentic AI in regulated contexts requires principled reasoning about two design dimensions: agency (what the system can do) and autonomy (how much it acts without human involvement). Though often treated independently, they are…
In decision support systems, it is essential to get a candidate solution fast, even if it means resorting to an approximation. This constraint introduces a scalability requirement with regard to the kind of heuristics which can be used in…
In this work, we describe a self-replication-based mechanism for designing agents of increasing complexity. We demonstrate the validity of this approach by solving simple, standard evolutionary computation problems in simulation. In the…
The usage of automated learning agents is becoming increasingly prevalent in many online economic applications such as online auctions and automated trading. Motivated by such applications, this paper is dedicated to fundamental modeling…
Our ability to build autonomous agents that leverage Generative AI continues to increase by the day. As builders and users of such agents it is unclear what parameters we need to align on before the agents start performing tasks on our…
The rapid development of advanced AI agents and the imminent deployment of many instances of these agents will give rise to multi-agent systems of unprecedented complexity. These systems pose novel and under-explored risks. In this report,…
Across millennia, complex societies have faced the same coordination problem of how to organize collective action among cognitively bounded and informationally incomplete individuals. Different civilizations developed different political…
AI is increasingly deployed in multi-agent systems; however, most research considers only the behavior of individual models. We experimentally show that multi-agent "AI organizations" are simultaneously more effective at achieving business…
While advances in multi-agent learning have enabled the training of increasingly complex agents, most existing techniques produce a final policy that is not designed to adapt to a new partner's strategy. However, we would like our AI agents…