# Instant Software Factories

DevFeed: [Instant Software Factories](<https://devfeed.tech/articles/instant-software-factories-103636.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.36254>)

Author: Wenxin Jiang, Mikola Lysenko

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Software](<https://devfeed.tech/topics/software.md>), [developer-productivity](<https://devfeed.tech/topics/developer-productivity.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [also](<https://devfeed.tech/tags/also.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [association](<https://devfeed.tech/tags/association.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [board](<https://devfeed.tech/tags/board.md>), [bootstrap](<https://devfeed.tech/tags/bootstrap.md>), [build](<https://devfeed.tech/tags/build.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [changes](<https://devfeed.tech/tags/changes.md>), [ci](<https://devfeed.tech/tags/ci.md>), [cli](<https://devfeed.tech/tags/cli.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [instant](<https://devfeed.tech/tags/instant.md>), [software](<https://devfeed.tech/tags/software.md>), [software-factories](<https://devfeed.tech/tags/software-factories.md>)

## AI overview

An instant software factory coordinates ongoing repository work with two inputs: cron-job agents following standing objectives and a shared communication board, such as GitHub, where they coordinate through recorded activity. A bootstrap prompt was distilled from two manually configured industrial factories to set up both inputs from one round of human input; it has not yet been evaluated. In the GitHub-coordinated CLI factory, daily merges rose 15-fold during agent rollout, an observed association. Agents filed 95% of new issues and authored 40 of 58 PRs changing CI workflows; at least 5.6% of issues marked fixed were later found to contain incorrect fixes. Because a factory changes its own workload and measures of progress, the authors frame its development as multi-objective optimization under endogenous feedback and plan further evolution and testing.

## Source excerpt

arXiv:2610.36254v1 Announce Type: new Abstract: Coding agents can quickly build prototypes, but a long tail of fixes, optimizations, tests, and releases separates a prototype from a product. A software factory handles this ongoing work through a repeatable process. We ask whether this work needs dedicated orchestration and how such factories should be judged. Given a tested repository and a coding agent, an instant software factory uses only two coordination inputs, a swarm of cron-job agents with standing objectives and a shared communication board, such as GitHub, where agents coordinate through the traces they leave. We developed a bootstrap prompt designed to set up both inputs from one round of human input, with governance as a separable layer. We distilled it from two manually configured industrial factories, observed for 15 and 17 days, and have not yet evaluated it. In the GitHub-coordinated CLI factory, daily merges rose 15x during agent rollout, an observed association. Its agents also filed 95% of new issues and authored 40 of 58 PRs that changed CI workflows, and at least 5.6% of issues marked as fixed were later found to have incorrect fixes. Unlike an agent scored on a fixed benchmark, a factory thus changes its own workload, evaluator, and measured progress. We formulate factory development as multi-objective optimization under this endogenous feedback. Over five months, we plan to evolve both factories, test the bootstrap on new repositories, and test five falsifiable hypotheses.