mlsanityData to 7 Oct 2026

IV Co-Scientist: Multi-Agent LLM Framework for Causal Instrumental Variable Discovery

arXiv 2602.07943 ↗First posted 8 Feb 2026cs.AIcited by 2

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

Abstract (arXiv)

In the presence of confounding between an endogenous variable and the outcome, instrumental variables (IVs) are used to isolate the causal effect of the endogenous variable. Identifying valid instruments requires interdisciplinary knowledge, creativity, and contextual understanding, making it a non-trivial task. In this paper, we investigate whether large language models (LLMs) can aid in this task. We perform a two-stage evaluation framework. First, we test whether LLMs can recover well-established instruments from the literature, assessing their ability to replicate standard reasoning. Second, we evaluate whether LLMs can identify and avoid instruments that have been empirically or theoretically discredited. Building on these results, we introduce IV Co-Scientist, a multi-agent system that proposes, critiques, and refines IVs for a given treatment-outcome pair. We also introduce a statistical test to contextualize consistency in the absence of ground truth. Our results show the potential of LLMs to discover valid instrumental variables from a large observational database.

Key facts. Cited by 2 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 21 of its 55 references that are in the map. First posted on arXiv 8 Feb 2026.

Builds on

21 of 55 references.

References · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  4. 2024Qwen2.5-Coder Technical Reportcited by 1,151
  5. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  6. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 348
  7. 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 348
  8. 2022Grounded Copilot: How Programmers Interact with Code-Generating Modelscited by 216
  9. 2023The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4cited by 112
  10. 2024Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agentscited by 94
  11. 2024AgentReview: Exploring Peer Review Dynamics with LLM Agentscited by 92
  12. 2023Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinementcited by 89
9 more
  1. 2023Can large language models build causal graphs?cited by 72
  2. 2024Evaluating and Enhancing Large Language Models for Novelty Assessment in Scholarly Publicationscited by 26
  3. 2024Large Language Models are Effective Priors for Causal Graph Discoverycited by 23
  4. 2023Self-Compatibility: Evaluating Causal Discovery without Ground Truthcited by 22
  5. 2023Demonstration of InsightPilot: An LLM-Empowered Automated Data Exploration Systemcited by 20
  6. 2024LitLLMs, LLMs for Literature Review: Are we there yet?cited by 12
  7. 2024Mining Causality: AI-Assisted Search for Instrumental Variablescited by 7
  8. 2024Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variablescited by 6
  9. 2018Necessary and Probably Sufficient Test for Finding Valid Instrumental Variablescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Evaluating Bivariate Causal Statements Based on Mutual Compatibilitycited by 0
  2. 2026CausalSmith: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inferencecited by 0

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. 2024Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery
  3. 2026Traceable Latent Variable Discovery Based on Multi-Agent Collaboration
  4. 2025CARE: Turning LLMs Into Causal Reasoning Expert
  5. 2025LLM-based Agents for Automated Confounder Discovery and Subgroup Analysis in Causal Inference
  6. 2025Can LLMs Leverage Observational Data? Towards Data-Driven Causal Discovery with LLMs
  7. 2025Beyond Correlation: Towards Causal Large Language Model Agents in Biomedicine
  8. 2024Multi-Agent Causal Discovery Using Large Language Models