AI 中文总结
该研究基于含1084名开发者的GitHub数据模拟发现，编码智能体（CA）可提升开源社区生产力，但采用率低且收益集中于活跃开发者，还会减少人类直接交互、降低公共知识实用性。
AI 中文摘要
开源软件社区是一种数字公共基础设施，不仅产出代码，还通过可见协作生成公共知识与人际关系。编码智能体（CAs）是提升开发效率的先进工具，同时将部分活动从公开的人类交互转移至私密的人类-智能体循环。本研究基于LLM的多智能体模拟开展，初始化数据来自1084名活跃开发者及其仓库关系的真实GitHub数据。在使用历史提交完成预热后，将同一社区状态分为无CA（No-CA）和有CA（CA）两种条件进行为期4周的平行模拟。引入CA后，计划完成的任务数量分别增加34.0%和39.0%，中位数完成时间从45分钟缩短至20分钟。但CA的采用率仅为26.0%，且收益集中在原本更活跃、连接更紧密的开发者群体中。CA还重构了任务执行路径：人类直接交互占比从32.4%降至11.6%，含CA的交互模式占比升至57.3%，其中40.3%通过CA辅助的自循环完成。CA条件下生成的公共知识对后续任务的支持更弱：在标准化检索基准中，CA语料的知识覆盖率为22.3%，远低于真实人类语料的81.1%，且需要更多检索步骤，成功率更低。这些结果揭示了生产力与公共知识的张力：编码智能体提升了技术产出，但更多工作转移至智能体介导或私密循环，使得公共记录对未来贡献者的实用性降低。
英文摘要
Open-source software communities are a form of digital public infrastructure that not only produces code, but also generates public knowledge and interpersonal relationships through visible collaboration. Generative coding agents (CAs) are an advanced tool to improve development efficiency while shifting part of activities from public human interaction to private human-agent loops. We study this shift using an LLM-based multi-agent simulation initialized with real GitHub data from 1,084 active developers and their repository relationships. After a warm-up with historical commits, we branch the same community state into parallel No-CA and CA conditions for 4-week simulations. CA introduction increases planned and completed tasks by 34.0% and 39.0%, respectively, and reduces median completion time from 45 to 20 minutes. However, adoption reaches only 26.0%, and the gains concentrate among developers who are already more active and well connected. CAs also restructure task execution pathways. Direct human-human interaction declines from 32.4% to 11.6%, while CA-involved modes increase to 57.3%, including 40.3% completed through CA-assisted self-loops. Public knowledge generated under CA condition also provides less support for later tasks. On a standardized retrieval benchmark, the CA corpus achieves 22.3% knowledge coverage, far below the 81.1% achieved by the real-human corpus, and requires more retrieval steps with a lower success rate. These results reveal a productivity-public knowledge tension: coding agents increase technical production, but more work shifts to agent-mediated or private loops, leaving public records less useful to future contributors.
