The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search

• 类型：arxiv
• 标识：2608.23252
• 链接：http://arxiv.org/abs/2608.23252v1
• 主分类：rag
• 形态：application
• TLDR：As Retrieval-Augmented Generation (RAG) shifts toward diverse portfolio generation, it is stymied by two critical bottlenecks: flawed measurement of evidence utilization, and suboptimal context budget allocation. We resolve both sequentially. To resolve measurement, we expose a pervasive ``diagnostic illusion'': standard relevance proxies fail catastrophically on hard negatives. We replace them with an efficient causal leave-one-out probe that accurately isolates generative reliance and formally calibrates the structural dilution of LLM attention. To resolve allocation, we deploy this causal p
• 待LLM分类：否
• 标题中文：上下文分配定律：生成式搜索中的因果度量与闭环编排
• TLDR中文：随着 Retrieval-Augmented Generation (RAG) 向多样化组合生成方向发展，它受到两个关键瓶颈的阻碍：对证据利用的度量有缺陷，以及上下文预算分配欠优。我们依次解决这两个问题。为解决度量问题，我们揭示了一种普遍的"诊断幻觉"：标准相关性代理在难负例上表现糟糕。我们用一种高效的因果留一探针来取代它们，该探针能够准确隔离生成式依赖关系，并形式化地校准 LLM 注意力的结构性稀释。为解决分配问题，我们部署该因果探针
• 来源文件：
• /inbox/tom/_candidates/2026-08-25-agent-rag-longcontext-candidates.json