Piper: On-device Environment Setup Via Online Reinforcement Learning | Awesome LLM Papers Add your paper to Awesome LLM Papers

Piper: On-device Environment Setup Via Online Reinforcement Learning

Alexander Kovrigin, Aleksandra Eliseeva, Konstantin Grotov, Egor Bogomolov, Yaroslav Zharov . No Venue 2025

[Code] [Paper]   Search on Google Scholar   Search on Semantic Scholar
Compositional Generalization Fine Tuning Has Code Interdisciplinary Approaches Llm For Code Model Architecture Multimodal Semantic Representation Reinforcement Learning Training Techniques

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.

Similar Work