Skip to content
NeurIPS 2026 planner

Poster · Atlanta

There are Levels to It: Red Teaming LLMs with Hierarchical Reinforcement Learning

When
Wed 9 Dec 2026, 16:30–19:30 EST
Where
Hall C1, Georgia World Congress Center
Session
Atlanta Poster Session 2
Authors
Roman Belaire, Arunesh Sinha, Pradeep Varakantham
Organisations
Carnegie Mellon University, Rutgers University, Singapore Management University
QRS classification
Reinforcement learning, Language models, Safety, fairness and privacy

Open in scheduleOfficial page