RAT: RunAnyThing via Fully Automated Environment Configuration
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913062087294976 |
|---|---|
| author | Huang, Renhong Hua, Dongdong Sun, Yifei Ding, Sitao Yuan, Hanyang Wang, Daixin Yang, Yang |
| author_facet | Huang, Renhong Hua, Dongdong Sun, Yifei Ding, Sitao Yuan, Hanyang Wang, Daixin Yang, Yang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_23190 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RAT: RunAnyThing via Fully Automated Environment Configuration Huang, Renhong Hua, Dongdong Sun, Yifei Ding, Sitao Yuan, Hanyang Wang, Daixin Yang, Yang Software Engineering Artificial Intelligence 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. |
| title | RAT: RunAnyThing via Fully Automated Environment Configuration |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2604.23190 |