mlsanityData to 14 Oct 2026

ORCA: ORchestrating Causal Agent

arXiv 2508.21304 ↗First posted 29 Aug 2025cs.DB cs.MAcited by 1

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

Abstract (arXiv)

Causal analysis on relational databases is challenging, as analysis datasets must be repeatedly queried from complex schemas. Recent LLM systems can automate individual steps, but they hardly manage dependencies across analysis stages, making it difficult to preserve consistency between causal hypothesis. We propose ORCA (ORchestrating Causal Agent), an interactive multi-agent framework to enable coherent causal analysis on relational databases by maintaining shared state and introducing human checkpoints. In a controlled user study, participants using ORCA successfully completed end-to-end analysis more often than with a baseline LLM (GPT-4o-mini) assistant by 42 percentage points, achieved substantially lower ATE error, and reduced time spent on repetitive data exploration and query refinement by 76% on average. These results show that ORCA improves both how users interact with the causal analysis pipeline and the reliability of the resulting causal conclusions.

Key facts. Cited by 1 paper 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 28 of its 52 references that are in the map. First posted on arXiv 29 Aug 2025.

Builds on

28 of 52 references.

References · 28

  1. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  2. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  3. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  4. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  5. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  6. 2015Estimation and Inference of Heterogeneous Treatment Effects using Random Forestscited by 600
  7. 2017Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learningcited by 478
  8. 2021AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Promptscited by 268
  9. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 164
  10. 2023Can Large Language Models Infer Causation from Correlation?cited by 146
  11. 2024DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoningcited by 125
  12. 2023Causal-learn: Causal Discovery in Pythoncited by 109
16 more
  1. 2020DoWhy: An End-to-End Library for Causal Inferencecited by 95
  2. 2020CausalML: Python Package for Causal Machine Learningcited by 74
  3. 2024AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitionscited by 70
  4. 2025Interactive Debugging and Steering of Multi-Agent AI Systemscited by 68
  5. 2022DoWhy-GCM: An extension of DoWhy for causal inference in graphical causal modelscited by 41
  6. 2025GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modelingcited by 36
  7. 2024LAMBDA: A Large Model Based Data Agentcited by 30
  8. 2024ALCM: Autonomous LLM-Augmented Causal Discovery Frameworkcited by 29
  9. 2021DoubleML -- An Object-Oriented Implementation of Double Machine Learning in Pythoncited by 23
  10. 2024Data Formulator 2: Iterative Creation of Data Visualizations, with AI Transforming Data Along the Waycited by 21
  11. 2020Causal Relational Learningcited by 13
  12. 2013A Sound and Complete Algorithm for Learning Causal Models from Relational Datacited by 12
  13. 2025Agent-S: LLM Agentic workflow to automate Standard Operating Procedurescited by 10
  14. 2022Learning Relational Causal Models with Cycles through Relational Acyclificationcited by 6
  15. 2025Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agentscited by 4
  16. 2025Relational Causal Discovery with Latent Confounderscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026CausalReasoningBenchmark: A Real-World Benchmark for Disentangled Evaluation of Causal Identification and Estimationcited by 6

Similar, not cited

Close in wording, no citation either way

  1. 2026CausalSteward: An Agentic Divide-Conquer-Combine Copilot for Causal Discovery
  2. 2025Causal-Copilot: An Autonomous Causal Analysis Agent
  3. 2026CausalAgent: A Conversational Multi-Agent System for End-to-End Causal Inference
  4. 2025Causal MAS: A Survey of Large Language Model Architectures for Discovery and Effect Estimation
  5. 2026CausalSmith: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference
  6. 2026Causal Discovery in the Era of Agents
  7. 2026CausalDS: Benchmarking Causal Reasoning in Data-Science Agents
  8. 2024Multi-Agent Causal Discovery Using Large Language Models