# CausalSteward: An Agentic Divide-Conquer-Combine Copilot for Causal Discovery

arXiv: https://arxiv.org/abs/2607.01936 · HTML: https://mlsanity.com/paper/2607.01936/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 57 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 30 of 30)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Differentiable Causal Discovery from Interventional Data](https://mlsanity.com/paper/2007.01754/) (2020)
- [Talk like a Graph: Encoding Graphs for Large Language Models](https://mlsanity.com/paper/2310.04560/) (2023)
- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (2023)
- [Integrating Large Language Model for Improved Causal Discovery](https://mlsanity.com/paper/2306.16902/) (2023)
- [Efficient Causal Graph Discovery Using Large Language Models](https://mlsanity.com/paper/2402.01207/) (2024)
- [Causal-Discovery Performance of ChatGPT in the context of Neuropathic Pain Diagnosis](https://mlsanity.com/paper/2301.13819/) (2023)
- [Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluation](https://mlsanity.com/paper/1906.01732/) (2019)
- [Integrating Large Language Models in Causal Discovery: A Statistical Causal Approach](https://mlsanity.com/paper/2402.01454/) (2024)
- [Can Foundation Models Talk Causality?](https://mlsanity.com/paper/2206.10591/) (2022)
- [Multi-Agent Causal Discovery Using Large Language Models](https://mlsanity.com/paper/2407.15073/) (2024)
- [Iterative Causal Discovery in the Possible Presence of Latent Confounders and Selection Bias](https://mlsanity.com/paper/2111.04095/) (2021)
- [Sample, estimate, aggregate: A recipe for causal discovery foundation models](https://mlsanity.com/paper/2402.01929/) (2024)
- [The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications](https://mlsanity.com/paper/2412.01953/) (2024)
- [Causal Identification under Markov Equivalence](https://mlsanity.com/paper/1812.06209/) (2018)
- [Zero-shot Causal Graph Extrapolation from Text via LLMs](https://mlsanity.com/paper/2312.14670/) (2023)
- [Causal-Copilot: An Autonomous Causal Analysis Agent](https://mlsanity.com/paper/2504.13263/) (2025)
- [On the Equivalence of Causal Models](https://mlsanity.com/paper/1304.1108/) (2013)
- [An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models](https://mlsanity.com/paper/2402.05359/) (2024)
- [The Causal Chambers: Real Physical Systems as a Testbed for AI Methodology](https://mlsanity.com/paper/2404.11341/) (2024)
- [Teaching Transformers Causal Reasoning through Axiomatic Training](https://mlsanity.com/paper/2407.07612/) (2024)
- [CausalGraph2LLM: Evaluating LLMs for Causal Queries](https://mlsanity.com/paper/2410.15939/) (2024)
- [Expert-Aided Causal Discovery of Ancestral Graphs](https://mlsanity.com/paper/2309.12032/) (2023)
- [DCILP: A Distributed Approach for Large-Scale Causal Structure Learning](https://mlsanity.com/paper/2406.10481/) (2024)
- [Mitigating Prior Errors in Causal Structure Learning: A Resilient Approach via Bayesian Networks](https://mlsanity.com/paper/2306.07032/) (2023)
- [Causal discovery using dynamically requested knowledge](https://mlsanity.com/paper/2310.11154/) (2023)
- [Local Causal Discovery with Background Knowledge](https://mlsanity.com/paper/2408.07890/) (2024)
- [CausalMan: A physics-based simulator for large-scale causality](https://mlsanity.com/paper/2502.12707/) (2025)
- [On the Unlikelihood of D-Separation](https://mlsanity.com/paper/2303.05628/) (2023)

## Abstract (arXiv)

Learning causal models from high-dimensional data is a significant challenge, particularly in real-world settings where violations of core assumptions lead to causal identifiability issues. Although massive amounts of prior knowledge are available, and contain valuable causal information, effectively integrating this knowledge into the causal discovery process remains an open problem. We introduce CausalSTeward (CAST), a novel human-in-the-loop framework for interactively assembling large causal models. CausalSteward is a multi-agent collaborative system that tackles high-dimensional causality through a divide-and-conquer approach where large clusters of variables are iteratively partitioned and then separately analyzed. Our framework fuses prior knowledge with a data-driven approach by using tailored tools such as retrieval augmented generation and conditional independence tests. Finally, we use this work to examine the capabilities and limitations of causal reasoning in multi-agent frameworks, and how the human-in-the-loop can contribute to accurate and trustworthy results.