ROTE: Modeling Human Behavior as Executable Programs for Improved AI Prediction
By
PaulHoule
7mo ago· 2 min readenInsight
75/100
Toasty
Bagelometer↗
Lightly browned and well buttered. A solid pick from the rack.
Score75TypeanalysisSentimentpositive
Summary
This research paper introduces ROTE, a novel algorithm that models human behavior as executable behavioral programs rather than traditional belief-desire frameworks. The approach uses large language models to synthesize behavioral programs and probabilistic inference to handle uncertainty, achieving up to 50% better performance than existing methods in predicting human and AI behaviors across gridworld tasks and household simulations.
Key quotes
· 4 pulledOur key insight is that many everyday social interactions may follow predictable patterns; efficient 'scripts' that minimize cognitive load for actors and observers
We propose modeling these routines as behavioral programs instantiated in computer code rather than policies conditioned on beliefs and desires
ROTE predicts human and AI behaviors from sparse observations, outperforming competitive baselines by as much as 50% in terms of in-sample accuracy and out-of-sample generalization
By treating action understanding as a program synthesis problem, ROTE opens a path for AI systems to efficiently and effectively predict human behavior in the real-world
Accurate prediction of human behavior is essential for robust and safe human-AI collaboration. However, existing approaches for modeling people are often data-hungry and brittle because they either make unrealistic assumptions about rationality or are too
