# Causal Agent based on Large Language Model

arXiv: https://arxiv.org/abs/2408.06849 · HTML: https://mlsanity.com/paper/2408.06849/

## Key facts

- Cited by 10 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 39 of its 70 references that are in the map.
- First posted on arXiv 13 Aug 2024.

## 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, 30 of 39)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [ChatGPT: Jack of all trades, master of none](https://mlsanity.com/paper/2302.10724/) (2023)
- [Causal Inference in the Presence of Latent Variables and Selection Bias](https://mlsanity.com/paper/1302.4983/) (2013)
- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (2023)
- [Can Large Language Models Infer Causation from Correlation?](https://mlsanity.com/paper/2306.05836/) (2023)
- [TableLlama: Towards Open Large Generalist Models for Tables](https://mlsanity.com/paper/2311.09206/) (2023)
- [RestGPT: Connecting Large Language Models with Real-World RESTful APIs](https://mlsanity.com/paper/2306.06624/) (2023)
- [Emergent autonomous scientific research capabilities of large language models](https://mlsanity.com/paper/2304.05332/) (2023)
- [ChatEDA: A Large Language Model Powered Autonomous Agent for EDA](https://mlsanity.com/paper/2308.10204/) (2023)
- [Score matching enables causal discovery of nonlinear additive noise models](https://mlsanity.com/paper/2203.04413/) (2022)
- [Causal-learn: Causal Discovery in Python](https://mlsanity.com/paper/2307.16405/) (2023)
- [CLadder: Assessing Causal Reasoning in Language Models](https://mlsanity.com/paper/2312.04350/) (2023)
- [Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation](https://mlsanity.com/paper/2305.07375/) (2023)
- [Table-GPT: Table-tuned GPT for Diverse Table Tasks](https://mlsanity.com/paper/2310.09263/) (2023)
- [Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data](https://mlsanity.com/paper/2402.17644/) (2024)
- [Out-of-domain Detection for Natural Language Understanding in Dialog Systems](https://mlsanity.com/paper/1909.03862/) (2019)

## Built on by (most cited first, 10 of 10)

- [Causality for Large Language Models](https://mlsanity.com/paper/2410.15319/) (2024)
- [CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language Models](https://mlsanity.com/paper/2502.11008/) (2025)
- [Simulating Society Requires Simulating Thought](https://mlsanity.com/paper/2506.06958/) (2025)
- [Towards Agentic AI on Particle Accelerators](https://mlsanity.com/paper/2409.06336/) (2024)
- [PhenoAssistant: A Conversational Multi-Agent AI System for Automated Plant Phenotyping](https://mlsanity.com/paper/2504.19818/) (2025)
- [Multi-agent Undercover Gaming: Hallucination Removal via Counterfactual Test for Multimodal Reasoning](https://mlsanity.com/paper/2511.11182/) (2025)
- [Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation](https://mlsanity.com/paper/2510.04504/) (2025)
- [Beyond Correlation: Towards Causal Large Language Model Agents in Biomedicine](https://mlsanity.com/paper/2505.16982/) (2025)
- [Mitigating Hidden Confounding by Progressive Confounder Imputation via Large Language Models](https://mlsanity.com/paper/2507.02928/) (2025)
- [CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations](https://mlsanity.com/paper/2604.14691/) (2026)

## Abstract (arXiv)

The large language model (LLM) has achieved significant success across various domains. However, the inherent complexity of causal problems and causal theory poses challenges in accurately describing them in natural language, making it difficult for LLM to comprehend and use them effectively. Causal methods are not easily conveyed through natural language, which hinders LLM's ability to apply them accurately. Additionally, causal datasets are typically tabular, while LLM excels in handling natural language data, creating a structural mismatch that impedes effective reasoning with tabular data. To address these challenges, we have equipped the LLM with causal tools within an agent framework, named the Causal Agent, enabling it to tackle causal problems. The causal agent comprises tools, memory, and reasoning modules. In the tool module, the causal agent calls Python code and uses the encapsulated causal function module to align tabular data with natural language. In the reasoning module, the causal agent performs reasoning through multiple iterations with the tools. In the memory module, the causal agent maintains a dictionary instance where the keys are unique names and the values are causal graphs. To verify the causal ability of the causal agent, we established a Causal Tabular Question Answer (CausalTQA) benchmark consisting of four levels of causal problems: variable level, edge level, causal graph level, and causal effect level. CausalTQA consists of about 1.4K for these four levels questions. Causal agent demonstrates remarkable efficacy on the four-level causal problems, with accuracy rates all above 80%. Through verification on the real-world dataset QRData, the causal agent is 6% higher than the original SOTA. For further insights and implementation details, our code is accessible via the GitHub repository https://github.com/kairong-han/causalagent.