This talk explores the cutting-edge development of a multi-agent AI system designed for open-ended game environments, with a focus on Minecraft. The presenter will discuss the creation of specialized AI agents, including a Vision Agent for spatial analysis, a Curriculum Agent for dynamic task generation, an Action Agent for behavior execution, a Critic Agent for performance evaluation, and a Skill Manager for knowledge retention. The presentation will highlight how these agents work together, leveraging advanced techniques like Reinforcement Learning, Chain of Thought, and Tree of Thought reasoning to enhance decision-making and adaptability. A key feature of this project is the multi-bot system, which enables multiple AI agents to operate concurrently in the same game world, fostering collaboration and skill sharing. By demonstrating the potential of AI-driven automation and adaptability in complex, dynamic environments, this research opens up exciting possibilities for applications beyond gaming.

As Large Language Models (LLMs) evolve, the challenge shifts from raw capability to structuring them into reliable, scalable systems. Many real-world AI products struggle with robustness, complexity management, and evaluation—especially in enterprise contexts. This talk explores how multi-agent systems can help overcome these obstacles by decomposing large monolithic agents into specialized subagents working together in structured architectures. We’ll cover: - Why enterprises struggle to integrate LLM agents effectively. - How multi-agent architectures (Assembly Line, Call Center, and Manager-Worker) improve scalability, modularity, and reliability. - Practical trade-offs and implementation strategies from real-world applications. (planning to adapt my post https://blog.sshh.io/p/building-multi-agent-systems)

Artificial Intelligence is transforming the way we interact with technology, and Agentic AI—systems that exhibit autonomy, adaptability, and decision-making capabilities—is at the forefront of this revolution. But what does this mean for the Arabic language, one of the richest and most complex languages in the world? As we advance AI-driven agents, ensuring they understand, process, and generate Arabic with the same fluency and nuance as English or other dominant languages is not just a technological challenge but a cultural imperative. In this speech, we will explore how Agentic AI can empower Arabic speakers, enhance accessibility, and preserve the linguistic heritage of over 400 million people while driving innovation across industries. The future of AI is agentic. The future of Arabic in AI depends on how we shape it today. Artificial Intelligence is transforming the way we interact with technology, and Agentic AI—systems that exhibit autonomy, adaptability, and decision-making capabilities—is at the forefront of this revolution. But what does this mean for the Arabic language, one of the richest and most complex languages in the world? As we advance AI-driven agents, ensuring they understand, process, and generate Arabic with the same fluency and nuance as English or other dominant languages is not just a technological challenge but a cultural imperative. In this speech, we will explore how Agentic AI can empower Arabic speakers, enhance accessibility, and preserve the linguistic heritage of over 400 million people while driving innovation across industries. The future of AI is agentic. The future of Arabic in AI depends on how we shape it today.

R1 > computer? In this talk, we will explore applying the ideas of R1 style RL fine-tuning for computer use

Agents are transforming how we approach problem-solving, automation, and user interaction. In this talk, I will explore the practical applications of agents, focusing on how they can deliver value. We'll discuss when agents are the right tool for the job, scenarios where they are not the right tool for the job, and strategies for deploying them to production with confidence and reliability. Whether you're new to agents or looking to refine your approach, this session offers actionable insights grounded in real-world experience.

AI Agents as Neuro-Symbolic Systems: Expanding the Boundaries of Intelligence" The current discourse around AI agents often centers on LLM-based systems with tool-calling capabilities, like REACT agents. While effective, this narrow definition limits the potential of agents to solve complex, real-world problems. In this talk, we explore a broader, more robust perspective—AI agents as neuro-symbolic systems. By combining neural networks' adaptability with the precision of symbolic reasoning, neuro-symbolic architectures bridge traditional AI approaches and modern advancements, enabling scalable and versatile workflows. This expanded definition accommodates not only LLMs but also embedding models, decision trees, and hybrid systems that integrate various modalities of intelligence. We will delve into: 1. The evolution of AI agents and the limitations of current models. 2. The core principles of neuro-symbolic systems and their practical applications. 3. A reimagined framework for building intelligent agents that operate flexibly across diverse tasks. This session aims to redefine the way we think about AI agents, empowering developers and researchers to design systems that are more efficient, resilient, and capable of tackling dynamic challenges. Join us as we explore the future of agentic AI and its transformative potential.

//Abstract AI has transformed industries, yet its true potential often lies untapped within core business processes. In this session, we’ll explore how AI agents differ from generative AI models, emphasizing their deterministic, hallucination-free approach to problem-solving. We’ll take a live example of an AI Agent in the logistics sector, and will detail the architectural foundations that enable AI agents to reason effectively, execute chain-of-thought workflows, and integrate seamlessly into human teams. We’ll discuss how these agents confidently navigate complex, multimodal tasks, extracting structured insights from unstructured data, and leveraging dynamic workflows for maximum flexibility. With customizable confidence thresholds, statefulness to track long-term cases, and advanced document understanding, these agents solve real business challenges, such as processing autonomously claims till resolution, with precision. Through a live case study, we’ll illustrate the measurable top and bottom-line effects of deploying AI agents—highlighting significant efficiency gains, multilingual capabilities, and safe, scalable applications in mission-critical environments. By showcasing how AI agents mimic human decision-making at unparalleled speed, we’ll inspire senior management to rethink AI’s role in their organizations and harness its full potential for transformative impact. //Bio Passionate about connecting deep tech to end-users, Vanessa’s work is at the forefront of AI’s transformative potential. For over a decade, she has been transforming cutting-edge innovations into actionable solutions that drive industry change. This is a bi-weekly "Agent Hour" event to continue the conversation about AI agents. Thanks to arcade-ai.com for the support! Join the next live event at home.mlops.community

//Abstract Demonstrating agents embedded within websites that utilize real-time audio and structured outputs to dynamically update web pages through conversational interactions. //Bio Raised in Reykjavík, living in Berlin. Studied computational and data science, did R&D in NLP and started making LLM apps as soon as GPT4 changed the game. This is a bi-weekly "Agent Hour" event to continue the conversation about AI agents. Thanks to arcade-ai.com for the support! Join the next live event at home.mlops.community