Saved in:
Bibliographic Details
Main Authors: Fu, Sihan, Liu, Oucheng, Wang, Shiyuan, Shi, Jin, Wei, Chengkun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.15815
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916016002433024
author Fu, Sihan
Liu, Oucheng
Wang, Shiyuan
Shi, Jin
Wei, Chengkun
author_facet Fu, Sihan
Liu, Oucheng
Wang, Shiyuan
Shi, Jin
Wei, Chengkun
contents Code agents increasingly help developers work with unfamiliar repositories, but every such task depends on a costly prerequisite: bootstrapping the repository into a usable development state. This process requires substantial trial-and-error exploration, yet the resulting knowledge--resolved dependencies, repair strategies--stays trapped in a single conversation, unavailable to future agents. We therefore formulate repository bootstrapping as a reusable startup knowledge problem and introduce BootstrapAgent, a multi-agent framework that distills the heuristics discovered during bootstrap exploration into a persistent, verifiable, agent-consumable .bootstrap contract. Through evidence extraction, structured planning, deterministic Docker-based verification, and trace-driven repair, BootstrapAgent generates a contract covering environment setup, diagnostic checks, minimal verification, and accumulated repair knowledge. We further propose warm repair with clean replay to accelerate iterative debugging without sacrificing cold-start reproducibility, and a delta repair with sanity check to prevent reward hacking. Experiments on three benchmarks show that BootstrapAgent achieves a 92.9% success rate, outperforming the baseline by over 10% while reducing downstream agent token usage by 25.9% and build time by 22.3%. Our code is available at https://github.com/Vossera/BootstrapAgent.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15815
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BootstrapAgent: Distilling Repository Setup into Reusable Agent Knowledge
Fu, Sihan
Liu, Oucheng
Wang, Shiyuan
Shi, Jin
Wei, Chengkun
Software Engineering
Computation and Language
Multiagent Systems
Code agents increasingly help developers work with unfamiliar repositories, but every such task depends on a costly prerequisite: bootstrapping the repository into a usable development state. This process requires substantial trial-and-error exploration, yet the resulting knowledge--resolved dependencies, repair strategies--stays trapped in a single conversation, unavailable to future agents. We therefore formulate repository bootstrapping as a reusable startup knowledge problem and introduce BootstrapAgent, a multi-agent framework that distills the heuristics discovered during bootstrap exploration into a persistent, verifiable, agent-consumable .bootstrap contract. Through evidence extraction, structured planning, deterministic Docker-based verification, and trace-driven repair, BootstrapAgent generates a contract covering environment setup, diagnostic checks, minimal verification, and accumulated repair knowledge. We further propose warm repair with clean replay to accelerate iterative debugging without sacrificing cold-start reproducibility, and a delta repair with sanity check to prevent reward hacking. Experiments on three benchmarks show that BootstrapAgent achieves a 92.9% success rate, outperforming the baseline by over 10% while reducing downstream agent token usage by 25.9% and build time by 22.3%. Our code is available at https://github.com/Vossera/BootstrapAgent.
title BootstrapAgent: Distilling Repository Setup into Reusable Agent Knowledge
topic Software Engineering
Computation and Language
Multiagent Systems
url https://arxiv.org/abs/2605.15815