# CausalDS: Benchmarking Causal Reasoning in Data-Science Agents

arXiv: https://arxiv.org/abs/2607.08093 · HTML: https://mlsanity.com/paper/2607.08093/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning.
- Builds on 36 of its 55 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Placed in

- LLM reasoning / [Causal reasoning in LLMs](https://mlsanity.com/lr/causal-reasoning-in-llms/)
- 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 36)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback](https://mlsanity.com/paper/2306.14898/) (2023)
- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (2023)
- [DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?](https://mlsanity.com/paper/2409.07703/) (2024)
- [MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers](https://mlsanity.com/paper/2508.20453/) (2025)
- [CLadder: Assessing Causal Reasoning in Language Models](https://mlsanity.com/paper/2312.04350/) (2023)
- [An Introduction to Proximal Causal Learning](https://mlsanity.com/paper/2009.10982/) (2020)
- [DoWhy: An End-to-End Library for Causal Inference](https://mlsanity.com/paper/2011.04216/) (2020)
- [Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data](https://mlsanity.com/paper/2402.17644/) (2024)
- [DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints](https://mlsanity.com/paper/2601.18137/) (2026)
- [MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering](https://mlsanity.com/paper/2505.07782/) (2025)
- [CausalBN-Bench: A Comprehensive Benchmark for Causal Learning Capability of LLMs](https://mlsanity.com/paper/2404.06349/) (2024)
- [AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?](https://mlsanity.com/paper/2606.05080/) (2026)
- [CausalGraph2LLM: Evaluating LLMs for Causal Queries](https://mlsanity.com/paper/2410.15939/) (2024)
- [LLMs are Overconfident: Evaluating Confidence Interval Calibration with FermiEval](https://mlsanity.com/paper/2510.26995/) (2025)
- [Ice Cream Doesn't Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal Inference](https://mlsanity.com/paper/2505.13770/) (2025)
- [CausalReasoningBenchmark: A Real-World Benchmark for Disentangled Evaluation of Causal Identification and Estimation](https://mlsanity.com/paper/2602.20571/) (2026)
- [OpenEstimate: Evaluating LLMs on Reasoning Under Uncertainty with Real-World Data](https://mlsanity.com/paper/2510.15096/) (2025)
- [Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification](https://mlsanity.com/paper/2601.21210/) (2026)
- [CausalGame: Benchmarking Causal Thinking of LLM Agents in Games](https://mlsanity.com/paper/2607.04293/) (2026)
- [Language Models as Causal Effect Generators](https://mlsanity.com/paper/2411.08019/) (2024)
- [Can Large Language Models Infer Causal Relationships from Real-World Text?](https://mlsanity.com/paper/2505.18931/) (2025)
- [RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades](https://mlsanity.com/paper/2605.15846/) (2026)
- [CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists](https://mlsanity.com/paper/2605.26029/) (2026)
- [EconCausal: A Context-Aware Economic Reasoning Benchmark for Large Language Models](https://mlsanity.com/paper/2510.07231/) (2025)

## Built on by (most cited first, 1 of 1)

- [CausalVerify: End-to-End Verification of Causal Analyses by Language Models](https://mlsanity.com/paper/2609.07944/) (2026)

## Abstract (arXiv)

Large language models (LLMs) increasingly act as data-science agents, combining abstract reasoning with advanced tool use. Yet the relevant benchmark landscape largely divides into symbolic causal reasoning benchmarks without realistic data analysis or data analysis benchmarks without causal data-generating structure or a range of causal data science tasks. Existing causal evaluation datasets are often restricted to curated examples from existing sources, with diversity coming from limited templatized variations rather than from systematic generation of novel synthetic causal structures. We introduce CausalDS, a benchmark for evaluating causal reasoning in agentic data-science workflows. Each benchmark instance is a scene consisting of a sampled structural causal model (SCM) with generated observational data and an accompanying synthetic natural-language story grounded in a real domain. We ground the composition of the benchmark components in empirical distributions obtained from real-world datasets, thus retaining empirical structure while reducing the memorization risk through completely synthetic generation. From each scene, we then derive tasks spanning all three of Pearl's rungs. Most tasks include a data science coding component, where the model typically needs to use several tools to arrive at the final answer due to imperfect observations. Abstention is tested directly: for targets the graph does not identify, the graded answer is to abstain. The benchmark thus jointly evaluates symbolic causal reasoning, data science, uncertainty quantification, abstention, and tool use/coding. Because the generator is fully synthetic, the exam is not a fixed dataset: composition, difficulty, and size are parameters, and fresh exams can be drawn at will.