Causal inference in social science relies on end-to-end, intervention-centered research-design reasoning grounded in real-world policy interventions, but current benchmarks fail to evaluate this capability of large language models (LLMs). We present InterveneBench, a benchmark designed to assess such reasoning in realistic social settings. Each instance in InterveneBench is derived from an empirical social science study and requires models to reason about policy interventions and identification assumptions without access to predefined causal graphs or structural equations. InterveneBench comprises 744 peer-reviewed studies across diverse policy domains. Experimental results show that state-of-the-art LLMs struggle under this setting. To address this limitation, we further propose a multi-agent framework, STRIDES. It achieves significant performance improvements over state-of-the-art reasoning models. Our code and data are available at https://github.com/Sii-yuning/STRIDES.
@article{arxiv.2603.15542,
title = {InterveneBench: Benchmarking LLMs for Intervention Reasoning and Causal Study Design in Real Social Systems},
author = {Shaojie Shi and Zhengyu Shi and Lingran Zheng and Xinyu Su and Anna Xie and Bohao Lv and Rui Xu and Zijian Chen and Zhichao Chen and Guolei Liu and Naifu Zhang and Mingjian Dong and Zhuo Quan and Bohao Chen and Teqi Hao and Yuan Qi and Yinghui Xu and Libo Wu},
journal= {arXiv preprint arXiv:2603.15542},
year = {2026}
}