mlsanityData to 7 Oct 2026

Multi-Agent Causal Discovery Using Large Language Models

arXiv 2407.15073 ↗First posted 21 Jul 2024cs.AI cs.CLcited by 26

On the map: LLM agents and tool use → Medical and scientific domain agents

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.

Key facts. Cited by 26 papers in the map (data through 7 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.

Builds on

25 of 75 references.

References · 25

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  6. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  7. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  8. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  9. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  10. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
  11. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 348
  12. 2023Large Language Models as Commonsense Knowledge for Large-Scale Task Planningcited by 231
13 more
  1. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 221
  2. 2013Causal Inference in the Presence of Latent Variables and Selection Biascited by 165
  3. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 153
  4. 2023Causal Parrots: Large Language Models May Talk Causality But Are Not Causalcited by 146
  5. 2023Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?cited by 104
  6. 2023Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debatecited by 94
  7. 2023Can large language models build causal graphs?cited by 72
  8. 2022LMPriors: Pre-Trained Language Models as Task-Specific Priorscited by 56
  9. 2024Integrating Large Language Models in Causal Discovery: A Statistical Causal Approachcited by 31
  10. 2024Large Language Models for Causal Discovery: Current Landscape and Future Directionscited by 25
  11. 2024Large Language Models are Effective Priors for Causal Graph Discoverycited by 23
  12. 2024Large Language Models for Constrained-Based Causal Discoverycited by 15
  13. 2024A Critical Review of Causal Reasoning Benchmarks for Large Language Modelscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 12; 2026: 12.

26 papers.

Sort:

By area:

  1. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 291
  2. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 167
  3. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 129
  4. 2024Causality for Large Language Modelscited by 24
  5. 2025A Survey of Scaling in Large Language Model Reasoningcited by 10
  6. 2025Large Causal Models from Large Language Modelscited by 8
  7. 2024Mining Causality: AI-Assisted Search for Instrumental Variablescited by 7
  8. 2025LLM Cannot Discover Causality, and Should Be Restricted to Non-Decisional Support in Causal Discoverycited by 7
  9. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systemscited by 5
  10. 2025Revealing Multimodal Causality with Large Language Modelscited by 3
  11. 2026PROMETHEUS: Automating Deep Causal Research Integrating Text, Data and Modelscited by 3
  12. 2025Causal MAS: A Survey of Large Language Model Architectures for Discovery and Effect Estimationcited by 2
14 more
  1. 2025A Roadmap Towards Improving Multi-Agent Reinforcement Learning With Causal Discovery And Inferencecited by 1
  2. 2025Multi-dimensional Data Analysis and Applications Basing on LLM Agents and Knowledge Graph Interactionscited by 1
  3. 2025CRAwDAD: Causal Reasoning Augmentation with Dual-Agent Debatecited by 1
  4. 2025ARCADIA: Scalable Causal Discovery for Corporate Bankruptcy Analysis Using Agentic AIcited by 1
  5. 2026Why LLMs Fail at Causal Discovery and How Interventional Agents Escapecited by 1
  6. 2026Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Modelscited by 1
  7. 2026CSQL: Mapping Documents into Causal Databasescited by 0
  8. 2026Step-by-Step Causality: Transparent Causal Discovery with Multi-Agent Tree-Query and Adversarial Confidence Estimationcited by 0
  9. 2026Multi-Agent Causal Reasoning System for Error Pattern Rule Automation in Vehiclescited by 0
  10. 2026CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulationscited by 0
  11. 2026TrialCalibre: A Fully Automated Causal Engine for RCT Benchmarking and Observational Trial Calibrationcited by 0
  12. 2026CausalSteward: An Agentic Divide-Conquer-Combine Copilot for Causal Discoverycited by 0
  13. 2026Conditional Independence Tests for Constraint-Based Causal Discovery: A Surveycited by 0
  14. 2026MaSCoD: A Multi-Agent Framework for Structural-Context-Guided Candidate Causal Graph Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting
  2. 2024Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery
  3. 2026Causal Discovery in the Era of Agents
  4. 2026Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach
  5. 2024LLM-initialized Differentiable Causal Discovery
  6. 2026Traceable Latent Variable Discovery Based on Multi-Agent Collaboration
  7. 2024ALCM: Autonomous LLM-Augmented Causal Discovery Framework
  8. 2026CausalArena: Benchmarking Causal Discovery in the Foundation Model Era