🎯 What is the Workshop About?

Large language models (LLMs) have revolutionized natural language processing, enabling powerful reasoning, planning, and tool use. Enterprises are increasingly adopting LLM-powered agents to automate workflows — from meeting summarization (e.g., Microsoft Copilot) to supply chain optimization and customer service orchestration. However, deploying agentic AI systems in enterprise settings introduces unique challenges:

• Designing multi-agent workflows

• Planning and reasoning in dynamic business environments

• Ensuring governance, security, and trustworthiness

• Building evaluation datasets and improving accuracy

• Keeping pace with fast-evolving frameworks (e.g., AutoGen, CrewAI)

• Adapting to new models like DeepSeek-R1

This workshop brings together academia and industry to explore the design, deployment, and evaluation of LLM-driven agents tailored for enterprise use.

🧭  Workshop Focus Areas

We’ll dive into three core themes:

1. Emerging Agentic Architectures & Platforms

2. Domain-Specific Applications

3. Evaluation, Governance, & Security Strategies