Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation

• 类型：arxiv
• 标识：2609.01601
• 链接：http://arxiv.org/abs/2609.01601v1
• 主分类：rag
• 形态：method
• TLDR：The repository-level code generation task requires synthesizing code that satisfies task requirements while remaining consistent with the target repository context. Since real-world repositories often exceed the input length limits of LLMs, existing approaches commonly adopt retrieval-augmented generation (RAG) to provide repository-specific context. Despite improving repository-context retrieval, existing methods typically provide context as task-level support, without explicitly identifying the critical tokens that require fine-grained repository context during generation. During the autoreg
• 待LLM分类：否
• 标题中文：自适应关键 token 感知的仓库级代码生成检索
• TLDR中文：仓库级代码生成任务需要合成满足任务需求且与目标仓库上下文保持一致的代码。由于真实仓库常超出 LLM 的输入长度限制，现有方法普遍采用 RAG 来提供仓库专属上下文。尽管现有方法改善了仓库上下文检索，但通常仅将上下文作为任务级支持，并未显式识别生成过程中需要细粒度仓库上下文的关键 token。在自回归
• 来源文件：
• /inbox/tom/_candidates/2026-09-02-agent-rag-longcontext-candidates.json