10 Reasons Your Multi-Agent Workflows Fail and What You Can Do About It

Multi-agent systems – a setup where multiple agents (generative AI models with access to tools) collaborate to solve complex tasks – are an emerging paradigm for building applications. Tools and frameworks like AutoGen make the development of multi-agent workflows more readily accessible to developers.

However, transitioning from experimentation to the development of reliable, production-ready systems remains challenging and somewhat unclear. As teams embrace and experiment with multi-agent systems, an increasingly important first step is to understand when and why this paradigm might fail. This talk highlights 10 common reasons these systems often fail based on early user feedback and the author’s work as a core maintainer of the AutoGen open-source Python framework (>1 million downloads, > 300 active contributors, > 18k users on Discord).


Speaker

Victor Dibia

Principal Research Software Engineer @Microsoft Research, Core Contributor to AutoGen, Author of "Multi-Agent Systems with AutoGen" book. Previously @Cloudera, @IBMResearch

Victor Dibia is a Principal Research Software Engineer at Microsoft Research where his current work is focused on the design of multi-agent systems powered by Generative AI models. Victor is a core contributor to AutoGen - a leading python open source library for building multi-agent applications and the creator of AutoGen Studio, a low code interface for authoring, testing and debugging multi-agent workflows. 

Read more
Find Victor Dibia at:

From the same track

Session AI/ML

Search: from Linear to Multiverse

Tuesday Nov 19 / 02:45PM PST

The future of search is undergoing a revolutionary transformation, shifting from traditional linear queries to a rich multiverse of possibilities powered by AI.

Speaker image - Faye Zhang

Faye Zhang

Staff Software Engineer @Pinterest, Tech Lead on GenAI Search Traffic Projects, Speaker, Expert in AI/ML with a Strong Background in Large Distributed System

Session LLMOps

Navigating LLM Deployment: Tips, Tricks, and Techniques

Tuesday Nov 19 / 01:35PM PST

Self-hosted Language Models are going to power the next generation of applications in critical industries like financial services, healthcare, and defense.

Speaker image - Meryem Arik

Meryem Arik

Co-Founder @TitanML, Recognized as a Technology Leader in Forbes 30 Under 30, Recovering Physicist

Session Generative AI

GenAI for Productivity

Tuesday Nov 19 / 11:45AM PST

At Wealthsimple, we leverage Generative AI internally to improve operational efficiency and streamline monotonous tasks. Our GenAI stack is a blend of tools we developed in house and third party solutions.

Speaker image - Mandy Gu

Mandy Gu

Senior Software Development Manager @Wealthsimple

Session Machine Learning

A Framework for Building Micro Metrics for LLM System Evaluation

Tuesday Nov 19 / 05:05PM PST

LLM accuracy is a challenging topic to address and is much more multi dimensional than a simple accuracy score. In this talk we’ll dive deeper into how to measure LLM related metrics, going through examples, case studies and techniques beyond just a single accuracy and score.

Speaker image - Denys Linkov

Denys Linkov

Head of ML @Voiceflow, LinkedIn Learning Instructor, ML Advisor and Instructor, Previously @LinkedIn

Session

Scaling Large Language Model Serving Infrastructure at Meta

Tuesday Nov 19 / 10:35AM PST

Running LLMs requires significant computational power, which scales with model size and context length. We will discuss strategies for fitting models to various hardware configurations and share techniques for optimizing inference latency and throughput at Meta.

Speaker image - Ye (Charlotte) Qi

Ye (Charlotte) Qi

Senior Staff Engineer @Meta