2nd Workshop: Deploying Autonomous Agents: Lessons, Risks, and Real-World Impact

As autonomous agents transition from research prototypes to real-world applications, the challenges of deployment take center stage. This workshop focuses on the practical dimensions of building, scaling, and maintaining agent-based systems across diverse domains. Topics will include deployment workflows, integration with existing software infrastructure, human-agent interaction, and lessons learned from early industry adopters.

We’ll also examine the social and organizational impact of deploying agents in the wild—from safety and alignment challenges to usability and evaluation frameworks. With contributions from both academic researchers and industry practitioners, this workshop aims to map the current frontier of agent deployment, spotlighting key successes, unresolved pain points, and emerging best practices. As 2025 unfolds as the “year of agents,” this gathering offers a timely opportunity to reflect on what’s working, what isn’t, and what’s coming next.

Jacob Andreas (MIT), Max Bartolo (Google DeepMind), Yonathan Belinkov (Technion – Israel Institute of Technology), Aaron Courville (IVADO, Université de Montréal, Mila), Verna Dankers (Mila, McGill University), Nouha Dziri (Allen Institute for AI (AI2)), Gauthier Gidel (IVADO, Université de Montréal, Mila), Seraphina Goldfarb-Tarrant (Cohere), Peter Henderson (Princeton University), Helen Nissenbaum (Cornell Tech), Vinodkumar Prabhakaran (Google), Siva Reddy (IVADO, McGill Univeristy, Mila), Jieyu Zhao (University of Southern California).

MONDAY, NOVEMBER 17TH, 2025

9:30 – 9.50 a.m.: Welcome and Registration

9:50 – 10 a.m.: Welcome Address

10 – 10:45 a.m.: Evaluating System-Level Reasoning in LLM Agents
Jacob Andreas (MIT)

10:45 – 11:30 a.m.: Don’t Forget the User: Balancing the Scales in Agentic Training and Evaluation
Seraphina Goldfarb-Tarrant (Cohere)

11:30 a.m. – 12 p.m.:  Recap. Discussion Audience/ G. Speakers

12 – 1.45 p.m.: Lunch on your Own

1.45 – 2.30 p.m.: Memorization: Myth or Mystery?
Verna Dankers (Mila, McGill University)

2.30 – 3.15 p.m.: Towards Scalable and Actionable Interpretability
Yonatan Belinkov (Technion – Israel Institute of Technology)

3.15 – 3.45 p.m.: Recap. Discussion Audience/ G. Speakers

3.45 – 5 p.m.: Social Hour/Mixer

TUESDAY, NOVEMBER 18TH, 2025

9:30 – 10 a.m.: Welcome and Coffee

10 – 10:45 a.m.: Building Better Rules and Optimization Targets for AI Agents
Peter Henderson (Princeton University)

10:45 – 11:30 a.m.: Reality is Adversarial: Towards Robust Real-World Agents
Max Bartolo (Google DeepMind)

11:30 a.m. – 12 p.m.:  Recap. Discussion Audience/ G. Speakers

12 – 1.45 p.m.: Lunch on your Own

1:45 – 2.30 p.m.: AI for the World of Many: Pluralism as a Core Principle
Vinodkumar Prabhakaran (Google)

2.30 – 3.15 p.m.: Human Extinction is Not the Worst that Could Happen
Helen Nissenbaum (Cornell Tech)

3.15 – 3.45 p.pm. : Coffee Break

3.45 – 5.15 p.m.: Panel: AI Agents: Slop or Substance?
Max Bartolo (Google DeepMind), Jacob Andreas (MIT), Vinodkumar Prabhakaran (Google), Helen Nissenbaum (Cornell Tech) & Peter Henderson (Princeton University)

WEDNESDAY, NOVEMBER 19TH, 2025

9:30 – 10 a.m.: Welcome and Coffee

10 – 10:45 a.m.: Cooperation and Collusion of Artificial Agents
Gauthier Gidel (IVADO, Université de Montréal, Mila)

10:45 – 11:30 a.m.: Learning to Cooperate: 
Training AI Agents for Social Dilemmas
Aaron Courville (IVADO, Université de Montréal, Mila)

11:30 a.m. – 12 p.m.:  Recap. Discussion Audience/ G. Speakers

12 – 2 p.m.: Lunch on your Own

2 – 2.45 p.m.: Value Drifts: Tracing Value Alignment During LLM Post-Training
Siva Reddy (IVADO, McGill University, Mila)

2.45 – 3.30 p.m.: LLM to Agent Safety: Emerging Societal and Technical Risks
Nouha Dziri (Allen Institute for AI (AI2))

3.30 – 4 p.m. : Coffee Break

4 – 4.45 p.m.: Building Personalized AI Assistants: From Task Execution to Human Alignment
Jieyu Zhao (University of Southern California)

4.45 – 5.15 p.m.: Recap. Discussion Audience/ G. Speakers

5.15 – 5.20 p.m.: Recap. on Semester and Closing Remarks