A new language-model agent framework that autonomously proposes, evaluates, and selects activities to satisfy multi-dimensional desires produces more human-like daily activity sequences in text-based simulations.
Everyday life sociology
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Simulating Human-like Daily Activities with Desire-driven Autonomy
A new language-model agent framework that autonomously proposes, evaluates, and selects activities to satisfy multi-dimensional desires produces more human-like daily activity sequences in text-based simulations.