# Multi-Agent Causal Discovery Using Large Language Models

arXiv: https://arxiv.org/abs/2407.15073 · HTML: https://mlsanity.com/paper/2407.15073/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 75 references that are in the map.
- First posted on arXiv 21 Jul 2024.

## 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, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Large Language Models as Commonsense Knowledge for Large-Scale Task Planning](https://mlsanity.com/paper/2305.14078/) (2023)
- [Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View](https://mlsanity.com/paper/2310.02124/) (2023)
- [Causal Inference in the Presence of Latent Variables and Selection Bias](https://mlsanity.com/paper/1302.4983/) (2013)
- [MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning](https://mlsanity.com/paper/2205.00445/) (2022)
- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (2023)
- [Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?](https://mlsanity.com/paper/2309.15943/) (2023)
- [Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate](https://mlsanity.com/paper/2305.11595/) (2023)
- [Can large language models build causal graphs?](https://mlsanity.com/paper/2303.05279/) (2023)
- [LMPriors: Pre-Trained Language Models as Task-Specific Priors](https://mlsanity.com/paper/2210.12530/) (2022)
- [Integrating Large Language Models in Causal Discovery: A Statistical Causal Approach](https://mlsanity.com/paper/2402.01454/) (2024)
- [Large Language Models for Causal Discovery: Current Landscape and Future Directions](https://mlsanity.com/paper/2402.11068/) (2024)
- [Large Language Models are Effective Priors for Causal Graph Discovery](https://mlsanity.com/paper/2405.13551/) (2024)
- [Large Language Models for Constrained-Based Causal Discovery](https://mlsanity.com/paper/2406.07378/) (2024)
- [A Critical Review of Causal Reasoning Benchmarks for Large Language Models](https://mlsanity.com/paper/2407.08029/) (2024)

## Built on by (most cited first, 26 of 26)

- [Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models](https://mlsanity.com/paper/2501.09686/) (2025)
- [AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges](https://mlsanity.com/paper/2505.10468/) (2025)
- [LLM Post-Training: A Deep Dive into Reasoning Large Language Models](https://mlsanity.com/paper/2502.21321/) (2025)
- [Causality for Large Language Models](https://mlsanity.com/paper/2410.15319/) (2024)
- [A Survey of Scaling in Large Language Model Reasoning](https://mlsanity.com/paper/2504.02181/) (2025)
- [LLM Cannot Discover Causality, and Should Be Restricted to Non-Decisional Support in Causal Discovery](https://mlsanity.com/paper/2506.00844/) (2025)
- [Large Causal Models from Large Language Models](https://mlsanity.com/paper/2512.07796/) (2025)
- [Mining Causality: AI-Assisted Search for Instrumental Variables](https://mlsanity.com/paper/2409.14202/) (2024)
- [Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.14892/) (2026)
- [Revealing Multimodal Causality with Large Language Models](https://mlsanity.com/paper/2509.17784/) (2025)
- [PROMETHEUS: Automating Deep Causal Research Integrating Text, Data and Models](https://mlsanity.com/paper/2605.12835/) (2026)
- [Causal MAS: A Survey of Large Language Model Architectures for Discovery and Effect Estimation](https://mlsanity.com/paper/2509.00987/) (2025)
- [A Roadmap Towards Improving Multi-Agent Reinforcement Learning With Causal Discovery And Inference](https://mlsanity.com/paper/2503.17803/) (2025)
- [Multi-dimensional Data Analysis and Applications Basing on LLM Agents and Knowledge Graph Interactions](https://mlsanity.com/paper/2510.15258/) (2025)
- [CRAwDAD: Causal Reasoning Augmentation with Dual-Agent Debate](https://mlsanity.com/paper/2511.22854/) (2025)
- [ARCADIA: Scalable Causal Discovery for Corporate Bankruptcy Analysis Using Agentic AI](https://mlsanity.com/paper/2512.00839/) (2025)
- [Why LLMs Fail at Causal Discovery and How Interventional Agents Escape](https://mlsanity.com/paper/2605.27567/) (2026)
- [Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models](https://mlsanity.com/paper/2606.27593/) (2026)
- [CSQL: Mapping Documents into Causal Databases](https://mlsanity.com/paper/2601.08109/) (2026)
- [Step-by-Step Causality: Transparent Causal Discovery with Multi-Agent Tree-Query and Adversarial Confidence Estimation](https://mlsanity.com/paper/2601.10137/) (2026)
- [Multi-Agent Causal Reasoning System for Error Pattern Rule Automation in Vehicles](https://mlsanity.com/paper/2602.01155/) (2026)
- [CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations](https://mlsanity.com/paper/2604.14691/) (2026)
- [TrialCalibre: A Fully Automated Causal Engine for RCT Benchmarking and Observational Trial Calibration](https://mlsanity.com/paper/2604.25832/) (2026)
- [CausalSteward: An Agentic Divide-Conquer-Combine Copilot for Causal Discovery](https://mlsanity.com/paper/2607.01936/) (2026)
- [Conditional Independence Tests for Constraint-Based Causal Discovery: A Survey](https://mlsanity.com/paper/2608.11156/) (2026)
- [MaSCoD: A Multi-Agent Framework for Structural-Context-Guided Candidate Causal Graph Generation](https://mlsanity.com/paper/2609.19944/) (2026)

## Abstract (arXiv)

Causal discovery aims to identify causal relationships between variables and is a fundamental problem across the sciences. Traditional statistical causal discovery (SCD) methods rely solely on observational data and ignore the contextual information available in metadata, whereas recent LLM-based methods exploit metadata but treat the large language model (LLM) as a single agent, leaving its judgments vulnerable to memorized or biased associations. To address this gap, we introduce MAC (Multi-Agent Causal Discovery Framework), which casts causal discovery as a multi-agent debate coupled with the autonomous selection of an SCD algorithm. MAC combines two complementary modules, bridged by a Meta Fusion mechanism: a Debate-Coding Module (DCM) that grounds an initial graph in data by autonomously selecting and executing the best-suited SCD algorithm, and a Meta-Debate Module (MDM) that refines the graph through an adversarial Affirmative-Negative-Judge debate over the metadata. Across five benchmark datasets and three metrics (F1, SHD, NHD), MAC achieves the best aggregate performance among five statistical and four LLM-based baselines, ranking first on 10 of 15 evaluation points with Gemini-2.0-Flash -- including a perfect reconstruction of the Earthquake graph -- and remains robust across three backbone LLMs.