mlsanityData to 14 Oct 2026

Step-by-Step Causality: Transparent Causal Discovery with Multi-Agent Tree-Query and Adversarial Confidence Estimation

arXiv 2601.10137 ↗First posted 15 Jan 2026cs.LG cs.AI stat.MLcited by 0

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

Abstract (arXiv)

Causal discovery aims to recover ``what causes what'', but classical constraint-based methods (e.g., PC, FCI) suffer from error propagation, and recent LLM-based causal oracles often behave as opaque, confidence-free black boxes. This paper introduces Tree-Query, a tree-structured, multi-expert LLM framework that reduces pairwise causal discovery to a short sequence of queries about backdoor paths, (in)dependence, latent confounding, and causal direction, yielding interpretable judgments with robustness-aware confidence scores. Theoretical guarantees are provided for asymptotic identifiability of four pairwise relations. On data-free benchmarks derived from Mooij et al. and UCI causal graphs, Tree-Query improves structural metrics over direct LLM baselines, and a diet--weight case study illustrates confounder screening and stable, high-confidence causal conclusions. Tree-Query thus offers a principled way to obtain data-free causal priors from LLMs that can complement downstream data-driven causal discovery. Code is available at https://anonymous.4open.science/r/Repo-9B3E-4F96.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 15 of its 22 references that are in the map. First posted on arXiv 15 Jan 2026.

Builds on

15 of 22 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Multi-Agent Causal Discovery Using Large Language Models21 Jul

Other references · 14

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  2. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  3. 2023Can large language models build causal graphs?cited by 73
  4. 2023Causal Discovery with Language Models as Imperfect Expertscited by 64
  5. 2023Integrating Large Language Model for Improved Causal Discoverycited by 54
  6. 2024Efficient Causal Graph Discovery Using Large Language Modelscited by 53
  7. 2024Large Language Models are Effective Priors for Causal Graph Discoverycited by 24
  8. 2024Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Modelscited by 16
  9. 2024Large Language Models for Constrained-Based Causal Discoverycited by 15
  10. 2016Estimating and Controlling the False Discovery Rate for the PC Algorithm Using Edge-Specific P-Valuescited by 8
  11. 2021Causal Structural Learning Via Local Graphscited by 7
  12. 2025Uncovering Bias Paths with LLM-guided Causal Discovery: An Active Learning and Dynamic Scoring Approachcited by 3
2 more
  1. 2025Causal Reasoning in Pieces: Modular In-Context Learning for Causal Discoverycited by 3
  2. 2018Too Fast Causal Inference under Causal Insufficiencycited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025LLM Cannot Discover Causality, and Should Be Restricted to Non-Decisional Support in Causal Discovery
  2. 2024LLM-initialized Differentiable Causal Discovery
  3. 2026CausalSteward: An Agentic Divide-Conquer-Combine Copilot for Causal Discovery
  4. 2026CausalArena: Benchmarking Causal Discovery in the Foundation Model Era
  5. 2026Traceable Latent Variable Discovery Based on Multi-Agent Collaboration
  6. 2026Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting
  7. 2026Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach
  8. 2026Why LLMs Fail at Causal Discovery and How Interventional Agents Escape