TCPO uses stepwise preference optimization and an action consistency constraint to raise ALFWorld average success from 20.0% to 26.7%.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making
TCPO uses stepwise preference optimization and an action consistency constraint to raise ALFWorld average success from 20.0% to 26.7%.