Skip to main content
Search

# Agentic Heterogeneous Treatment Effects Benchmark

1 related articles

Subscribe to updates
  1. arXiv

    Agent-retrieved covariates need three checks: date filtering alone lets encoder weights carry future facts

    Language-model agents can retrieve fast-moving local context that survey baselines miss, but whether such covariates are usable for causal analysis needs separate verification. A pilot study anchored on Uganda's Youth Opportunities Program compares two retrieval workflows across 11 datasets and 47 treatment-outcome contrasts, with checks on retrieval timing, out-of-sample ranking and pretrained encoder weights. Neither workflow dominates, and swapping the encoder alone shifts downstream heterogeneity rankings.

You’re all caught up