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

arXiv: https://arxiv.org/abs/2602.07943 · HTML: https://mlsanity.com/paper/2602.07943/

## Key facts

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

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4](https://mlsanity.com/paper/2311.07361/) (2023)
- [Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents](https://mlsanity.com/paper/2410.13185/) (2024)
- [AgentReview: Exploring Peer Review Dynamics with LLM Agents](https://mlsanity.com/paper/2406.12708/) (2024)
- [Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement](https://mlsanity.com/paper/2310.08559/) (2023)
- [Can large language models build causal graphs?](https://mlsanity.com/paper/2303.05279/) (2023)
- [Evaluating and Enhancing Large Language Models for Novelty Assessment in Scholarly Publications](https://mlsanity.com/paper/2409.16605/) (2024)
- [Large Language Models are Effective Priors for Causal Graph Discovery](https://mlsanity.com/paper/2405.13551/) (2024)
- [Self-Compatibility: Evaluating Causal Discovery without Ground Truth](https://mlsanity.com/paper/2307.09552/) (2023)
- [Demonstration of InsightPilot: An LLM-Empowered Automated Data Exploration System](https://mlsanity.com/paper/2304.00477/) (2023)
- [LitLLMs, LLMs for Literature Review: Are we there yet?](https://mlsanity.com/paper/2412.15249/) (2024)
- [Mining Causality: AI-Assisted Search for Instrumental Variables](https://mlsanity.com/paper/2409.14202/) (2024)
- [Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables](https://mlsanity.com/paper/2409.02604/) (2024)
- [Necessary and Probably Sufficient Test for Finding Valid Instrumental Variables](https://mlsanity.com/paper/1812.01412/) (2018)

## Built on by (most cited first, 2 of 2)

- [CausalSmith: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference](https://mlsanity.com/paper/2607.22511/) (2026)
- [Evaluating Bivariate Causal Statements Based on Mutual Compatibility](https://mlsanity.com/paper/2606.00278/) (2026)

## 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.