Interpreting Agent Behavior
Description
The First Workshop on Human-Centered Interpretation for Understanding Agents, Humans, and Interaction at NeurIPS 2026 aims to study agent behavior at three levels: the agent, the human, and their interaction. It focuses on gathering the community to identify the problem space and emerging challenges while bridging social science and AI communities.
Event location
Let your network know you`re going
Share this event to start conversations, invite colleagues, and connect before it begins.
Meet the speakers
Diyi Yang
Theme:Stanford University, Human-centered NLP
Nancy F. Chen
Theme:Dr. Nancy F. Chen from A*STAR focusing on human-centered frontier AI.
Armando Solar-Lezama
Theme:MIT CSAIL, Program Synthesis
Been Kim
Theme:Google DeepMind, Agentic Interpretability
Marc-Alexandre Côté
Theme:Microsoft Research, RL & Language Agents
Bowen Baker
Theme:OpenAI, Multi-Agent Systems
Dinh Phung
Theme:Monash University, Robust & Reliable Agents
Kun Zhang
Theme:Carnegie Mellon University & MBZUAI, Causal Discovery
Related events
AI Workshop - Katherine
DevDay Exchange Community: Sydney
Startup Networking⚡& Fireside Chat w/ Rye Smith (Claude Ambassador, Founder & Investor
PauseAI WA: Local Chapter Meet
The Future of HR: Generative AI for Hiring, Engagement & Leadership | Perth
OBM: Getting more from MS Copilot
Graduation equals unemployment? AI is reshaping your profession
