3 papers
cs.AI2026
Human-Guided Harm Recovery for Computer Use Agents
Christy Li, Sky CH-Wang, Andi Peng +1
As LM agents gain the ability to execute actions on real computer systems, we need ways to not only prevent harmful actions at scale but also effectively remediate harm when preven…
cs.AI2024
Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge
Weihua Du, Qiushi Lyu, Jiaming Shan +8
We introduce Constrained Human-AI Cooperation (CHAIC), an inclusive embodied social intelligence challenge designed to test social perception and cooperation in embodied agents. In…
cs.LG2024
Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input
Andi Peng, Yuying Sun, Tianmin Shu +1
Humans use social context to specify preferences over behaviors, i.e. their reward functions. Yet, algorithms for inferring reward models from preference data do not take this soci…