PACT is an ask-or-act framework using reinforcement learning on interaction history to decide when to seek clarification, improving assistance accuracy and a new clarification utility metric over passive baselines in multi-day embodied scenarios.
arXiv preprint arXiv:2409.10849 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
MindZero is a self-supervised RL framework that trains MLLMs for online Theory of Mind reasoning by rewarding mental-state hypotheses that best explain observed actions via a planner, then distills this into fast inference.
citing papers explorer
-
PACT: Proactive Asking for Continual Task Assistance in Human-Robot Collaboration
PACT is an ask-or-act framework using reinforcement learning on interaction history to decide when to seek clarification, improving assistance accuracy and a new clarification utility metric over passive baselines in multi-day embodied scenarios.
-
MindZero: Learning Online Mental Reasoning With Zero Annotations
MindZero is a self-supervised RL framework that trains MLLMs for online Theory of Mind reasoning by rewarding mental-state hypotheses that best explain observed actions via a planner, then distills this into fast inference.