发表机构
Alibaba Group（阿里巴巴集团）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对仓库级代码推理的上下文限制与关系图维护问题，该研究提出带任务条件关系实例化的仅实体外部接口，经DeepSeek-V4-Flash和SWE-bench Verified评估，双层索引方案在零预构建边时成功率达95.6%。
AI 中文摘要
大型软件仓库常超出模型上下文限制，将仓库知识训练入模型成本高且易过时；本地检索可能遗漏分散的需求，显式关系图则会带来持续维护负担。我们提出仅含实体的外部接口，在推理时进行任务条件关系实例化，采用双层索引区分全局路由与局部实体聚焦，并在DeepSeek-V4-Flash和SWE-bench Verified上评估，在零预构建实体-关系边的情况下，基础单层与双层条件分别达到92.1%、94.2%和95.6%的成功率。
英文摘要
Large software repositories are often beyond model context limits. Training repository knowledge into models is costly and quickly stale, while local retrieval can miss scattered requirements, and explicit relation graphs add ongoing maintenance burden. We propose an entity-only external interface with task-conditioned relation materialization during inference. A two-layer index separates global routing from local entity focus and is evaluated on DeepSeek-V4-Flash and SWE-bench Verified. The base, one-layer, and two-layer conditions achieve 92.1%, 94.2%, and 95.6% success, respectively, under zero pre-built entity-relation edges.
Comments9 pages, 2 figures,
