[PDG 475] MASS: Multi-Agent Design: Optimizing Agents with Better Prompts & Top.

Link to article: https://arxiv.org/pdf/2502.02533
Title: MASS: Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies
Track: Automated Agent Optimization
Content: MASS is an optimization framework for multi-agent systems that automates the design of both prompts and interaction topologies through a three-stage process: local prompt optimization, topology optimization, and global prompt optimization. The framework demonstrates that jointly optimizing prompts and topologies is critical for effective multi-agent system design, significantly outperforming existing approaches.
Slack link: ml-ka.slack.com, channel: #pdg. Please join us -- if you cannot join, please message us here or to mlpaperdiscussiongroupka@gmail.com.

In the Paper Discussion Group (PDG) we discuss recent and fundamental papers in the area of machine learning on a weekly basis. If you are interested, please read the paper beforehand and join us for the discussion. If you have not fully understood the paper, you can still participate – everyone is welcome! You can join the discussion or simply listen in. The discussion is in German or English depending on the participants.