Towards Agentic Intelligence: Architectures for Multi-Agent AI Systems

## Event Logistics

2 DAY EVENT! Saturday 11/15 AND Sunday 11/16 (details below)

Students Register for the class at this Eventbrite Link.
https://www.eventbrite.com/e/towards-agentic-intelligence-architectures-for-multi-agent-ai-systems-tickets-1799266537649?aff=SFbayACMmeetup

Pricing, with discounts that stack
* 10% discount when signing up for both days with one purchase
* 20% early bird discount
* NEW: 50% student/unemployed discount. To get the discount code, email proof of full time enrollment or unemployment to . Use the email subject "ACM multi-agent PDS: discount". There is a limited number.

* 50% BOGO discount. Buy one ticket and sign up two people, for a limited number of tickets. This 50% discount does not include the regular food or drink. This discount stacks with "early bird", "student" or "2 days" discounts.

All pricing includes a $20 annual membership to the SFbayACM

We accept optional donations to our non-profit organization, which is tax deductible. SFbayACM’s Non-Profit Taxpayer ID: 31-0963922
In past years, we have given $3,500 to support STEM education, judging 1,000+ science fair projects at the Synopsis Science Fair, https://science-fair.org/

Day 1, Labs (details below)

• Saturday, Nov 15 8:30am to 5pm
• Sign up for a limited number of seats in person at
• Valley Research Park, 319 North Bernardo Ave, Mountain View, CA.
• Go to the right side of the building, 2nd door
• Coffee breaks and lunch is included in the price
• Zoom for a remote audience
• Both the local and remote audience will be supported by TA’s. The moderator will watch the Zoom chat for questions for the speaker, and ask them.
• Remote tickets have a built in discount, because food is not provided

Day 2, Lectures (outlined below)

• Sunday, Nov 16, 9am to 5pm, only on Zoom
• Zoom for a remote audience
• The remote audience will be supported by questions that can be directed to the speaker by the moderator
• Remote tickets have a built in discount, because food is not provided

## Overview

Building on the tremendous response to Dhanashree Lele’s ACM talk on Multi-Agent Architectures for Enterprise AI, this 2-day, research-caliber, hands-on workshop is designed to advance the state of practice in Agentic AI system design, evaluation, and optimization.
This workshop will guide participants through theory-to-deployment workflows for constructing next-generation multi-agent frameworks, benchmarking agentic behaviors, and applying compute-efficient orchestration strategies. The curriculum draws heavily from recent breakthroughs presented at NeurIPS, ICLR, and KDD, grounding hands-on engineering in rigorous scientific principles and reproducible experimentation.
By bridging academic research and production-grade engineering, this workshop is ideal for applied researchers, industry practitioners, graduate students, and technical leaders seeking to design reliable, interpretable, and high-performance LLM-based agentic systems.

## Learning Format and Structure

This intensive two-day workshop follows a progressive “build-as-you-learn” methodology. Each module introduces core research concepts followed by guided implementation in Jupyter/Google Colab, enabling participants to translate theory directly into working systems.

### 📅 Day 1 — Architecting Multi-Agent Systems

• 4 hands-on labs focused on:
• Building multi-agentic systems/use-cases from first principles
• Exploring agent tools, MCP operability, and orchestration strategies
• Converting agentic prototypes into robust, production-ready cognitive pipelines

### 📅 Day 2 — Deep Dive: Research Frontiers and Reproduction

• Analytical walkthroughs of seminal and frontier papers in Agentic AI from NeurIPS, ICLR, and KDD
• Structured methodology for paper-to-prototype translation: reproducing cutting-edge research through practical labs
• Discussions on evaluation benchmarks, alignment frameworks, and emergent behavior analysis

## Key Outcomes

Theoretical Foundations: Understand the mathematical and algorithmic underpinnings of multi-agent LLM architectures, orchestration, and alignment.
Hands-On Mastery: Gain practical experience in building agentic systems from scratch, configuring MCP operability, and scaling prototypes into production-grade deployments.
**Evaluation & Governance:**Learn to design and apply alignment and evaluation frameworks to ensure robustness, interpretability, and responsible deployment of multi-agent systems.
Practical Assets: Walk away with fully functional notebooks, baseline reference architectures, curated reading lists, and reproducible workflows to accelerate implementation in your own organization.
ACM Certificate for completing the class.

## Prerequisites

• Intermediate to advanced Python programming is nice-to-have. However, if you are a manager, product manager, CTO or other that wants exposure to the technology, you can still get alot out of the class. You can run code in a Jupyter Notebook step by step.
• Familiarity with APIs and Jupyter/Colab environments is helpful.
• Experience with or interest in LLMs (OpenAI API will be used; open-source alternatives such as Claude, Mistral, and Llama 3 will also be discussed)

## Who Should Attend

• AI/ML Engineers, Data Scientists & AI Practitioners designing or deploying LLM applications
• Applied Researchers & Postdocs exploring Agentic AI, neuro-symbolic systems, or autonomous orchestration
• Technical Leaders & Architects integrating multi-agent reasoning in production environments