Preprint · 2026

Read the Paper, Write the Code: Agentic Reproduction of Social-Science Results

Benjamin Kohler, David Zollikofer, Johanna Einsiedler, Alexander Hoyle, Elliott Ash

Abstract

Recent work has used LLM agents to reproduce empirical social science results with access to both the data and code. We broaden this scope by asking: Can they reproduce results given only a paper's methods description and original data? We develop an agentic reproduction system that extracts structured methods descriptions from papers, runs reimplementations under strict information isolation -- agents never see the original code, results, or paper -- and enables deterministic, cell-level comparison of reproduced outputs to the original results. An error attribution step traces discrepancies through the system chain to identify root causes. Evaluating four agent scaffolds and four LLMs on 48 papers with human-verified reproducibility, we find that agents can largely recover published results, but performance varies substantially between models, scaffolds, and papers. Root cause analysis reveals that failures stem both from agent errors and from underspecification in the papers themselves.

BibTeX Copy

@misc{kohler_read_2026,
	title = {Read the {Paper}, {Write} the {Code}: {Agentic} {Reproduction} of {Social}-{Science} {Results}},
	shorttitle = {Read the {Paper}, {Write} the {Code}},
	url = {http://arxiv.org/abs/2604.21965},
	doi = {10.48550/arXiv.2604.21965},
	abstract = {Recent work has used LLM agents to reproduce empirical social science results with access to both the data and code. We broaden this scope by asking: Can they reproduce results given only a paper's methods description and original data? We develop an agentic reproduction system that extracts structured methods descriptions from papers, runs reimplementations under strict information isolation -- agents never see the original code, results, or paper -- and enables deterministic, cell-level comparison of reproduced outputs to the original results. An error attribution step traces discrepancies through the system chain to identify root causes. Evaluating four agent scaffolds and four LLMs on 48 papers with human-verified reproducibility, we find that agents can largely recover published results, but performance varies substantially between models, scaffolds, and papers. Root cause analysis reveals that failures stem both from agent errors and from underspecification in the papers themselves.},
	urldate = {2026-11-06},
	publisher = {arXiv},
	author = {Kohler, Benjamin and Zollikofer, David and Einsiedler, Johanna and Hoyle, Alexander and Ash, Elliott},
	month = sep,
	year = {2026},
	note = {arXiv:2604.21965 [cs.AI]},
	keywords = {Computer Science - Artificial Intelligence},
}