# PROMETHEUS: Automating Deep Causal Research Integrating Text, Data and Models

arXiv: https://arxiv.org/abs/2605.12835 · HTML: https://mlsanity.com/paper/2605.12835/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 6 of its 26 references that are in the map.
- First posted on arXiv 13 May 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 6 of 6)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Multi-Agent Causal Discovery Using Large Language Models](https://mlsanity.com/paper/2407.15073/) (2024)
- [A Survey on Extraction of Causal Relations from Natural Language Text](https://mlsanity.com/paper/2101.06426/) (2021)
- [Large Causal Models from Large Language Models](https://mlsanity.com/paper/2512.07796/) (2025)

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

- [Latent Confounded Causal Discovery via Lie Bracket Geometry](https://mlsanity.com/paper/2606.19610/) (2026)
- [Kan Extension Transformers: A Categorical Unification of Attention, Diffusion, and Predict-Detach Self-Conditioning](https://mlsanity.com/paper/2605.27259/) (2026)
- [Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models](https://mlsanity.com/paper/2606.27593/) (2026)

## Abstract (arXiv)

Large language models can extract local causal claims from text, but those claims become more useful when organized as persistent, navigable world models rather than as flat summaries. We introduce PROMETHEUS, a framework that turns retrieved literature, filings, reviews, reports, agent traces, source data, code, simulations, and scientific models into causal atlases: sheaf-like families of local causal predictive-state models over an explicit cover of a research substrate. Each local region contains causal episodes, structured claim tables, predictive tests, support statistics, and provenance; restriction maps compare overlapping regions; gluing diagnostics expose agreement, drift, contradiction, and underdetermination. The resulting Topos World Model is not a single universal graph. It is a research instrument for navigating what a corpus says, where it says it, how strongly it is supported, and where local claims fail to assemble into a coherent global view. Three literature-atlas case studies -- ocean-temperature impacts on marine populations, GLP-1 weight-loss evidence, and resveratrol/red-wine health-benefit claims -- illustrate deep causal research from text with explicit locality, evidence, persistent state, and gluing tension. Four grounded-counterfactual case studies -- a Nature Climate Change microplastics forcing paper, an Indus Valley hydrology paper with VIC-derived figure data and model code, the canonical Sachs protein-signaling study with single-cell perturbation data, and a Nature singing-mouse study with MAPseq projection matrices -- show a stronger mode: when a paper ships source data, simulation outputs, or code, PROMETHEUS can evaluate a counterfactual against that scientific substrate and then rebuild the sheaf world model around the