mlsanityData to 7 Oct 2026

Causal Discovery in the Era of Agents

arXiv 2606.23608 ↗First posted 22 Jun 2026cs.AI cs.LG cs.SEcited by 0

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

Abstract (arXiv)

Recent attempts to combine large language models (LLMs) with causal discovery ask models to infer pairwise directions, propose graph structures, or inject language-model outputs as priors and constraints. These approaches promise faster analysis, but they also obscure whether a causal evidence is supported by data and assumptions or by textual associations, prompt artifacts and hallucinated mechanisms. We argue for a different role for agents in causal discovery. Agents should inspect data, retrieve context, explain method assumptions and clarify graph outputs, but they should not supply edges, orientations, priors, constraints or causal conclusions. We propose the principle that agents assist the workflow, while causal claims remain grounded in data, explicit assumptions, formal algorithms, diagnostics and user or domain-expert decisions. We instantiate this principle in causal-learn+, an online platform that coordinates data analysis, preprocessing, method recommendation, expert-knowledge incorporation, formal discovery and interpretation around the algorithmic ecosystem of causal-learn. A case study on Big Five personality data illustrates agent-assisted pipeline of causal discovery without turning language-model unreliability into causal evidence. The platform is available at causallearn.com.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 13 of its 37 references that are in the map. First posted on arXiv 22 Jun 2026.

Builds on

13 of 37 references.

References · 13

  1. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 348
  2. 2019Causal Discovery from Heterogeneous/Nonstationary Data with Independent Changescited by 166
  3. 2013Causal Inference in the Presence of Latent Variables and Selection Biascited by 165
  4. 2023Causal-learn: Causal Discovery in Pythoncited by 108
  5. 2023Can large language models build causal graphs?cited by 72
  6. 2022Greedy Relaxations of the Sparsest Permutation Algorithmcited by 63
  7. 2023Causal Discovery with Language Models as Imperfect Expertscited by 62
  8. 2018Causal Discovery in the Presence of Missing Datacited by 46
  9. 2023Fast Scalable and Accurate Discovery of DAGs Using the Best Order Score Search and Grow-Shrink Treescited by 38
  10. 2023A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variablescited by 33
  11. 2024Integrating Large Language Models in Causal Discovery: A Statistical Causal Approachcited by 31
  12. 2013Theory Refinement on Bayesian Networkscited by 28
1 more
  1. 2024Large Language Models are Effective Priors for Causal Graph Discoverycited by 23

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Causal MAS: A Survey of Large Language Model Architectures for Discovery and Effect Estimation
  2. 2026Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach
  3. 2024Multi-Agent Causal Discovery Using Large Language Models
  4. 2025Causal-Copilot: An Autonomous Causal Analysis Agent
  5. 2026CausalAgent: A Conversational Multi-Agent System for End-to-End Causal Inference
  6. 2026Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
  7. 2026CausalDS: Benchmarking Causal Reasoning in Data-Science Agents
  8. 2026Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting