CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference

-->

Statistics > Machine Learning

arXiv:2607.22511v1 (stat)

[Submitted on 24 Jul 2026]

Title: CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference

Authors: Jiyuan Tan , Vasilis Syrgkanis

View a PDF of the paper titled CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference, by Jiyuan Tan and 1 other authors

View PDF HTML (experimental)

Abstract: Automating theoretical research is constrained not only by the generation of candidate results, but also by their reliable evaluation. A common approach is to close the research loop with a large language model (LLM) reviewer. However, such reviewers remain empirically unreliable: they may accept fabricated papers and detect them at rates close to chance (Bad Scientist, 2025). We present CausalForge, a framework for automated theoretical research in causal inference grounded in the Lean proof assistant. CausalForge combines Causalean, a foundational Lean library for causal inference containing 7,035 machine-checked declarations developed with language-model assistance under human design and review, with CausalSmith, a self-improving agentic pipeline that selects research topics, proposes results, formalizes statements, constructs proofs, and presents the resulting artifacts for human inspection. Because a machine-checke

…