Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiverse

• URL: http://arxiv.org/abs/2602.18710v1
• Date: Sat, 21 Feb 2026 04:10:21 GMT
• Title: Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiverse
• Authors: Martin Bertran, Riccardo Fogliato, Zhiwei Steven Wu,
• Abstract summary: We show that fully autonomous AI analysts built on large language models (LLMs) can reproduce a similar structured analytic diversity cheaply and at scale.<n>We show that the effects are emphsteerable: reassigning the analyst persona or LLM shifts the distribution of outcomes even after excluding methodologically deficient runs.
• Score: 22.927943525772857
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The conclusions of empirical research depend not only on data but on a sequence of analytic decisions that published results seldom make explicit. Past ``many-analyst" studies have demonstrated this: independent teams testing the same hypothesis on the same dataset regularly reach conflicting conclusions. But such studies require months of coordination among dozens of research groups and are therefore rarely conducted. In this work, we show that fully autonomous AI analysts built on large language models (LLMs) can reproduce a similar structured analytic diversity cheaply and at scale. We task these AI analysts with testing a pre-specified hypothesis on a fixed dataset, varying the underlying model and prompt framing across replicate runs. Each AI analyst independently constructs and executes a full analysis pipeline; an AI auditor then screens each run for methodological validity. Across three datasets spanning experimental and observational designs, AI analyst-produced analyses display wide dispersion in effect sizes, $p$-values, and binary decisions on supporting the hypothesis or not, frequently reversing whether a hypothesis is judged supported. This dispersion is structured: recognizable analytic choices in preprocessing, model specification, and inference differ systematically across LLM and persona conditions. Critically, the effects are \emph{steerable}: reassigning the analyst persona or LLM shifts the distribution of outcomes even after excluding methodologically deficient runs.

Related papers

• Exploring the Garden of Forking Paths in Empirical Software Engineering Research: A Multiverse Analysis [3.6324565773746147]
  We conduct a so-called multiverse analysis on a published empirical SE paper.<n>We identify nine pivotal analytical decisions with at least one equally defensible alternative.<n>The overwhelming majority produced qualitatively different, and sometimes even opposite, findings.
  arXiv  Detail & Related papers  (2025-12-09T18:47:00Z)
• Statistical Hypothesis Testing for Auditing Robustness in Language Models [49.1574468325115]
  We introduce distribution-based perturbation analysis, a framework that reformulates perturbation analysis as a frequentist hypothesis testing problem.<n>We construct empirical null and alternative output distributions within a low-dimensional semantic similarity space via Monte Carlo sampling.<n>We show how we can quantify response changes, measure true/false positive rates, and evaluate alignment with reference models.
  arXiv  Detail & Related papers  (2025-06-09T17:11:07Z)
• Automating Exploratory Multiomics Research via Language Models [22.302672656499315]
  PROTEUS is a fully automated system that produces data-driven hypotheses from raw data files.<n>We apply PROTEUS to clinical proteogenomics, a field where effective downstream data analysis and hypothesis proposal is crucial for producing novel discoveries.
  arXiv  Detail & Related papers  (2025-06-09T09:44:21Z)
• BLADE: Benchmarking Language Model Agents for Data-Driven Science [21.682416167339635]
  LM-based agents equipped with planning, memory, and code execution capabilities have the potential to support data-driven science.<n>We present BLADE, a benchmark to automatically evaluate agents' multifaceted approaches to open-ended research questions.
  arXiv  Detail & Related papers  (2024-08-19T02:59:35Z)
• Bayesian Federated Inference for Survival Models [0.0]
  In cancer research, overall survival and progression free survival are often analyzed with the Cox model. Merging data sets from different medical centers may help, but this is not always possible due to strict privacy legislation and logistic difficulties. Recently, the Bayesian Federated Inference (BFI) strategy for generalized linear models was proposed.
  arXiv  Detail & Related papers  (2024-04-26T15:05:26Z)
• Can Large Language Models emulate an inductive Thematic Analysis of semi-structured interviews? An exploration and provocation on the limits of the approach and the model [0.0]
  The paper presents results and reflection of an experiment done to use the model GPT 3.5-Turbo to emulate some aspects of an inductive Thematic Analysis. The objective of the paper is not to replace human analysts in qualitative analysis but to learn if some elements of LLM data manipulation can to an extent be of support for qualitative research.
  arXiv  Detail & Related papers  (2023-05-22T13:16:07Z)
• DRFLM: Distributionally Robust Federated Learning with Inter-client Noise via Local Mixup [58.894901088797376]
  federated learning has emerged as a promising approach for training a global model using data from multiple organizations without leaking their raw data. We propose a general framework to solve the above two challenges simultaneously. We provide comprehensive theoretical analysis including robustness analysis, convergence analysis, and generalization ability.
  arXiv  Detail & Related papers  (2022-04-16T08:08:29Z)
• Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets [53.34152466646884]
  In this paper, we show how bringing recent results on equivariant representation learning instantiated on structured spaces together with simple use of classical results on causal inference provides an effective practical solution. We demonstrate how our model allows dealing with more than one nuisance variable under some assumptions and can enable analysis of pooled scientific datasets in scenarios that would otherwise entail removing a large portion of the samples.
  arXiv  Detail & Related papers  (2022-03-29T04:54:06Z)
• A comprehensive comparative evaluation and analysis of Distributional Semantic Models [61.41800660636555]
  We perform a comprehensive evaluation of type distributional vectors, either produced by static DSMs or obtained by averaging the contextualized vectors generated by BERT. The results show that the alleged superiority of predict based models is more apparent than real, and surely not ubiquitous. We borrow from cognitive neuroscience the methodology of Representational Similarity Analysis (RSA) to inspect the semantic spaces generated by distributional models.
  arXiv  Detail & Related papers  (2021-05-20T15:18:06Z)
• Stable Prediction via Leveraging Seed Variable [73.9770220107874]
  Previous machine learning methods might exploit subtly spurious correlations in training data induced by non-causal variables for prediction. We propose a conditional independence test based algorithm to separate causal variables with a seed variable as priori, and adopt them for stable prediction. Our algorithm outperforms state-of-the-art methods for stable prediction.
  arXiv  Detail & Related papers  (2020-06-09T06:56:31Z)
• Balance-Subsampled Stable Prediction [55.13512328954456]
  We propose a novel balance-subsampled stable prediction (BSSP) algorithm based on the theory of fractional factorial design. A design-theoretic analysis shows that the proposed method can reduce the confounding effects among predictors induced by the distribution shift. Numerical experiments on both synthetic and real-world data sets demonstrate that our BSSP algorithm significantly outperforms the baseline methods for stable prediction across unknown test data.
  arXiv  Detail & Related papers  (2020-06-08T07:01:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.