Schedule
Date: July 31st, 2025
Location: Austria Center Vienna (map)
Room: 1.61-62
Program Schedule
| Time | Event |
|---|---|
| 08:45 - 09:00 | Opening Remarks |
| 09:00 - 09:30 | Invited Talk 1: Nicolas Chapados Agentic Full-Stack Benchmarking for Knowledge Work |
| 09:30 - 10:00 | Invited Talk 2: Siva Reddy The Path to Scalable and Safe Web Agents |
| 10:00 - 10:30 | Oral presentations (5 min each) + 5 min buffer David Guzman Piedrahita: Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games Devansh Srivastav: Safe in Isolation, Dangerous Together: Agent-Driven Multi-Turn Decomposition Jailbreaks on LLMs Christopher Cui: TALES- Text Adventure Learning Environment Suite Amrutha Varshini Ramesh: AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery Yicheng Fu: CAMPHOR: Collaborative Agents for Multi-input Planning and High-Order Reasoning On Device |
| 10:30 - 11:30 | Coffee Break & Poster session 1 |
| 11:30 - 12:00 | Invited Talk 3: Roberta Raileanu Automating AI Research: How Far Are We? |
| 12:00 - 12:30 | Invited Talk 4: Chris Manning Linguistic Agents that Learn from Interactions |
| 12:30 - 13:30 | Lunch Break |
| 13:30 - 14:00 | Invited Talk 5: Tao Yu Open Foundations for Computer-Use Agents |
| 14:00 - 14:30 | Invited Talk 6: Yu Su Augmenting Human Cognition with AI Agents that Use Computers |
| 14:30 - 15:00 | Invited Talk 7: Daniel Fried Inducing Functions to Improve LLM Agents |
| 15:00 - 16:00 | Coffee Break & Poster session 2 |
| 16:00 - 17:00 | Panel Discussion: Nicolas Chapados, Roberta Raileanu, Yu Su, Diyi Yang |
| 17:00 - 17:15 | Closing Remarks |