PIPer: On-Device Environment Setup via Online Reinforcement Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914094839234560 |
|---|---|
| author | Kovrigin, Alexander Eliseeva, Aleksandra Grotov, Konstantin Bogomolov, Egor Zharov, Yaroslav |
| author_facet | Kovrigin, Alexander Eliseeva, Aleksandra Grotov, Konstantin Bogomolov, Egor Zharov, Yaroslav |
| contents | Environment setup-the process of configuring the system to work with a specific software project-represents a persistent challenge in Software Engineering (SE). Automated environment setup methods could assist developers by providing fully configured environments for arbitrary repositories without manual effort. This also helps SE researchers to scale execution-based benchmarks. However, recent studies reveal that even state-of-the-art Large Language Models (LLMs) achieve limited success in automating this task. To address this limitation, we tune a specialized model for environment setup. We combine supervised fine-tuning for generating correct Bash scripts and Reinforcement Learning with Verifiable Rewards (RLVR) to adapt it to the task of environment setup. On EnvBench-Python, our method enables Qwen3-8B (a model runnable on consumer hardware) to perform on par with larger models-Qwen3-32B and GPT-4o. The training code and model checkpoints are available online: https://github.com/JetBrains-Research/PIPer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25455 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PIPer: On-Device Environment Setup via Online Reinforcement Learning Kovrigin, Alexander Eliseeva, Aleksandra Grotov, Konstantin Bogomolov, Egor Zharov, Yaroslav Machine Learning Artificial Intelligence Software Engineering Environment setup-the process of configuring the system to work with a specific software project-represents a persistent challenge in Software Engineering (SE). Automated environment setup methods could assist developers by providing fully configured environments for arbitrary repositories without manual effort. This also helps SE researchers to scale execution-based benchmarks. However, recent studies reveal that even state-of-the-art Large Language Models (LLMs) achieve limited success in automating this task. To address this limitation, we tune a specialized model for environment setup. We combine supervised fine-tuning for generating correct Bash scripts and Reinforcement Learning with Verifiable Rewards (RLVR) to adapt it to the task of environment setup. On EnvBench-Python, our method enables Qwen3-8B (a model runnable on consumer hardware) to perform on par with larger models-Qwen3-32B and GPT-4o. The training code and model checkpoints are available online: https://github.com/JetBrains-Research/PIPer. |
| title | PIPer: On-Device Environment Setup via Online Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2509.25455 |