- Updated: August 23, 2026
- 2 min read
Causal Agent based on Large Language Model
Causal Agent based on Large Language Model
Abstract: 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 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.
We verified the causal ability of the causal agent using the Causal Tabular Question Answer (CausalTQA) benchmark, which consists of four levels of causal problems: variable level, edge level, causal graph level, and causal effect level. CausalTQA contains about 1.4K questions across these levels. The causal agent demonstrates remarkable efficacy on the four‑level causal problems, achieving accuracy rates above 80 % on each level. On the real‑world dataset QRData, the causal agent outperforms the previous state‑of‑the‑art by 6 %.
For implementation details and code, visit the GitHub repository. Learn more about our related work and tools at Ubos.tech Blog.
Andrii Bidochko
CTO UBOS
Andrii Bidochko is an AI entrepreneur and researcher focused on AI agents, reinforcement learning, and autonomous systems. He writes about the technologies shaping the future of machine intelligence, from frontier models and agent architectures to real-world AI applications.