Causal Discovery in the Era of Agents

Hugging Face Daily Papers Papers

Summary

This paper argues that language model agents should assist causal discovery workflows by providing contextual support and explanations rather than generating causal conclusions, and introduces causal-learn+ platform to demonstrate this principle.

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.
Original Article
View Cached Full Text

Cached at: 06/23/26, 05:40 AM

Paper page - Causal Discovery in the Era of Agents

Source: https://huggingface.co/papers/2606.23608

Abstract

Language models should assist causal discovery workflows by providing contextual support and explanations rather than generating causal conclusions, as demonstrated through a platform that integrates data analysis and expert knowledge.

Recent attempts to combinelarge language models(LLMs) withcausal discoveryask 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 incausal 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, whilecausal claimsremain grounded in data, explicit assumptions,formal algorithms, diagnostics and user or domain-expert decisions. We instantiate this principle incausal-learn+, an online platform that coordinatesdata analysis, preprocessing, method recommendation,expert-knowledge incorporation, formal discovery and interpretation around the algorithmic ecosystem ofcausal-learn. A case study on Big Five personality data illustrates agent-assisted pipeline ofcausal discoverywithout turning language-model unreliability into causal evidence. The platform is available at causallearn.com.

View arXiv pageView PDFProject pageGitHub1.64kAdd to collection

Get this paper in your agent:

hf papers read 2606\.23608

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.23608 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.23608 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.23608 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists

Hugging Face Daily Papers

CausaLab is a scalable environment for evaluating LLM agents on interactive causal discovery, assessing both predictive accuracy and faithful recovery of underlying causal mechanisms. Experiments reveal a gap between prediction and mechanism recovery, highlighting limits in current LLM agents as experimental causal reasoners.

CausalDS: Benchmarking Causal Reasoning in Data-Science Agents

arXiv cs.AI

Introduces CausalDS, a benchmark for evaluating causal reasoning in LLM-based data science agents, using synthetic structural causal models and natural language stories to test associational, interventional, and counterfactual reasoning along with tool use and abstention.