OpenAI: Multi-Agent Systems (MAS)

Multi AI Agent Systems using OpenAI's new GPT-4o Model - API - OpenAI Developer Forum

Multi-Agent System Project - Community - OpenAI Developer Forum

Multi-agent systems | The Alan Turing Institute

Multi-agent systems (MAS) are a core area of research of contemporary artificial intelligence. A multi-agent system consists of multiple decision-making agents which interact in a shared environment to achieve common or conflicting goals. MAS research spans a range of technical problems, such as how to design MAS to incentivise certain behaviours in agents, how to design algorithms enabling one or more agents to achieve specified goals in a MAS, how information is communicated and propagated among agents, and how norms, conventions and roles may emerge in MAS. A vast array of applications can be addressed using MAS methodologies, including autonomous driving, multi-robot factories, automated trading, commercial games, automated tutoring, etc.

Structured Outputs for Multi-Agent Systems | OpenAI Cookbook

Structured Outputs is a new capability that builds upon JSON mode and function calling to enforce a strict schema in a model output.

By using the new parameter strict: true, we are able to guarantee the response abides by a provided schema.

When using function calling, if the number of functions (or tools) increases, the performance may suffer.

To mitigate this, we can logically group the tools together and have specialized "agents" that are able to solve specific tasks or sub-tasks, which will increase the overall system performance.