# Accelerating Social Science Research via Agentic Hypothesization and Experimentation

arXiv: https://arxiv.org/abs/2602.07983 · HTML: https://mlsanity.com/paper/2602.07983/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 43 references that are in the map.
- First posted on arXiv 8 Feb 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 12 of 12)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement](https://mlsanity.com/paper/2310.08559/) (2023)
- [Hypothesis Generation with Large Language Models](https://mlsanity.com/paper/2404.04326/) (2024)
- [Automated Hypothesis Validation with Agentic Sequential Falsifications](https://mlsanity.com/paper/2502.09858/) (2025)
- [HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation](https://mlsanity.com/paper/2504.11524/) (2025)
- [AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise](https://mlsanity.com/paper/2507.00310/) (2025)
- [Sparse Autoencoders for Hypothesis Generation](https://mlsanity.com/paper/2502.04382/) (2025)
- [Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck](https://mlsanity.com/paper/2310.19660/) (2023)
- [Measuring and Improving Persuasiveness of Large Language Models](https://mlsanity.com/paper/2410.02653/) (2024)
- [ChangeMyView Through Concessions: Do Concessions Increase Persuasion?](https://mlsanity.com/paper/1806.03223/) (2018)
- [Teaching Human Behavior Improves Content Understanding Abilities Of LLMs](https://mlsanity.com/paper/2405.00942/) (2024)

## Built on by (most cited first, 3 of 3)

- [Autonomous Scientific Discovery via Iterative Meta-Reflection](https://mlsanity.com/paper/2607.01131/) (2026)
- [StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery](https://mlsanity.com/paper/2606.11851/) (2026)
- [Open-ended Scientific Discovery with Possibilistic Reasoning](https://mlsanity.com/paper/2610.11289/) (2026)

## Abstract (arXiv)

Data-driven social science research is inherently slow, relying on iterative cycles of observation, hypothesis generation, and experimental validation. While recent data-driven methods promise to accelerate parts of this process, they largely fail to support end-to-end scientific discovery. To address this gap, we introduce EXPERIGEN, an agentic framework that operationalizes end-to-end discovery through a Bayesian optimization inspired two-phase search, in which a Generator proposes candidate hypotheses and an Experimenter evaluates them empirically. Across multiple domains, EXPERIGEN consistently discovers 2-4x more statistically significant hypotheses that are 7-17 percent more predictive than prior approaches, and naturally extends to complex data regimes including multimodal and relational datasets. Beyond statistical performance, hypotheses must be novel, empirically grounded, and actionable to drive real scientific progress. To evaluate these qualities, we conduct an expert review of machine-generated hypotheses, collecting feedback from senior faculty. Among 25 reviewed hypotheses, 88 percent were rated moderately or strongly novel, 70 percent were deemed impactful and worth pursuing, and most demonstrated rigor comparable to senior graduate-level research. Finally, recognizing that ultimate validation requires real-world evidence, we conduct the first A/B test of LLM-generated hypotheses, observing statistically significant results with p less than 1e-6 and a large effect size of 344 percent.