RAT: RunAnyThing via Fully Automated Environment Configuration

TL;DR

RAT is a language-agnostic framework that automates environment configuration for arbitrary repositories, significantly improving setup success rates in real-world scenarios.

Contribution

The paper introduces RAT, a fully automated, language-agnostic environment configuration framework with a multi-stage pipeline and a new benchmark for evaluation.

Findings

RAT achieves a 29.6% higher Environment Setup Success Rate than baselines.

RAT supports arbitrary repositories without language restrictions.

Extensive experiments validate RAT's state-of-the-art performance.

Abstract

Automating repository-level software engineering tasks is a foundational challenge for autonomous code agents, largely due to the difficulty of configuring executable environments. However, manual configuration remains a labor-intensive bottleneck, necessitating a transition toward fully automated environment configuration. Existing approaches often rely on pre-defined artifacts or are restricted to specific programming languages, limiting their applicability to real-world repositories. In this paper, we first propose RAT (RunAnyThing), a language-agnostic framework for automated environment configuration on arbitrary repositories. RAT features a multi-stage pipeline that integrates semantic initialization, a planning mechanism, specialized toolset, and a robust sandbox for configuration. Furthermore, to enable rigorous evaluation, we propose RATBench, a benchmark that reflects the the distribution and heterogeneity of real-world repositories. Extensive experiments demonstrate that RAT achieves state-of-the-art performance, improving the Environment Setup Success Rate (ESSR) by an average of 29.6% over strong baselines.