AI Trends 2025: AI Agents and Multi-Agent Systems with Victor Dibia - 718

Today we’re joined by Victor Dibia, principal research software engineer at Microsoft Research, to explore the key trends and advancements in AI agents and multi-agent systems shaping 2025 and beyond. In this episode, we discuss the unique abilities that set AI agents apart from traditional software systems–reasoning, acting, communicating, and adapting. We also examine the rise of agentic foundation models, the emergence of interface agents like Claude with Computer Use and OpenAI Operator, the shift from simple task chains to complex workflows, and the growing range of enterprise use cases. Victor shares insights into emerging design patterns for autonomous multi-agent systems, including graph and message-driven architectures, the advantages of the “actor model” pattern as implemented in Microsoft’s AutoGen, and guidance on how users should approach the ”build vs. buy” decision when working with AI agent frameworks. We also address the challenges of evaluating end-to-end agent performance, the complexities of benchmarking agentic systems, and the implications of our reliance on LLMs as judges. Finally, we look ahead to the future of AI agents in 2025 and beyond, discuss emerging HCI challenges, their potential for impact on the workforce, and how they are poised to reshape fields like software engineering. 🎧 / 🎥 Listen or watch the full episode on our page: https://twimlai.com/go/718. 🔔 Subscribe to our channel for more great content just like this: https://youtube.com/twimlai?sub_confirmation=1 🗣️ CONNECT WITH US! =============================== Subscribe to the TWIML AI Podcast: https://twimlai.com/podcast/twimlai/ Follow us on Twitter: https://twitter.com/twimlai Follow us on LinkedIn: https://www.linkedin.com/company/twimlai/ Join our Slack Community: https://twimlai.com/community/ Subscribe to our newsletter: https://twimlai.com/newsletter/ Want to get in touch? Send us a message: https://twimlai.com/contact/ 📖 CHAPTERS =============================== 00:00 - Introduction 7:18 - Defining agents 10:57 - AI Rewind 2024: AI Agents 21:58 - Agent native foundation models 30:14 - Task-specific and general-purpose tools 33:53 - Abstractions in complex agentic systems 39:10 - AutoGen architecture and emerging patterns 52:43 - Agents controlling browsers 1:01:10 - Political barriers in agentic bots 1:03:50 - Agentic noise 1:07:05 - Evaluation of end-to-end agentic performance 1:13:11 - Multi-agent systems 1:17:52 - Complex task framework 1:21:18 - Build vs. buy of agentic frameworks 1:26:08 - Observability and low-level and high-level APIs 1:29:16 - 2025 Predictions 1:35:07 - Impact on software engineering careers 🔗 LINKS & RESOURCES =============================== AI Agents 2024 Rewind - A Year of Building and Learning - https://newsletter.victordibia.com/p/ai-agents-2024-rewind-a-year-of-building AutoGen - https://github.com/microsoft/autogen Multi-Agent Systems with Autogen Book - https://multiagentbook.com/ Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks - https://www.microsoft.com/en-us/research/articles/magentic-one-a-generalist-multi-agent-system-for-solving-complex-tasks/ Why Agents Are Stupid & What We Can Do About It with Dan Jeffries - 713 - https://twimlai.com/podcast/twimlai/why-agents-are-stupid-what-we-can-do-about-it/ 📸 Camera: https://amzn.to/3TQ3zsg 🎙️Microphone: https://amzn.to/3t5zXeV 🚦Lights: https://amzn.to/3TQlX49 🎛️ Audio Interface: https://amzn.to/3TVFAIq 🎚️ Stream Deck: https://amzn.to/3zzm7F5