A scaffolded, human-in-the-loop agentic workflow outperforms less structured LLM baselines and matches hand-tuned methods on several observational causal inference benchmarks.
Title resolution pending
1 Pith paper cite this work, alongside 1 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1
external citations · OpenAlex
fields
stat.CO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Human-Augmenting Agentic Workflow for Observational Causal Inference
A scaffolded, human-in-the-loop agentic workflow outperforms less structured LLM baselines and matches hand-tuned methods on several observational causal inference benchmarks.