Retrieval-augmented generation (RAG) is highly sensitive to the quality of selected context, yet standard top-k retrieval often returns redundant or near-duplicate chunks that waste token budget and degrade downstream generation. We present AdaGReS, a redundancy-aware context selection framework for token-budgeted RAG that optimizes a set-level objective combining query-chunk relevance and intra-set redundancy penalties. AdaGReS performs greedy selection under a token-budget constraint using marginal gains derived from the objective, and introduces a closed-form, instance-adaptive calibration of the relevance-redundancy trade-off parameter to eliminate manual tuning and adapt to candidate-pool statistics and budget limits. We further provide a theoretical analysis showing that the proposed objective exhibits epsilon-approximate submodularity under practical embedding similarity conditions, yielding near-optimality guarantees for greedy selection. Experiments on open-domain question answering (Natural Questions) and a high-redundancy biomedical (drug) corpus demonstrate consistent improvements in redundancy control and context quality, translating to better end-to-end answer quality and robustness across settings.

翻译：检索增强生成（RAG）对所选上下文的质量高度敏感，然而标准的 top-k 检索通常会返回冗余或近似重复的文本块，这不仅浪费令牌预算，还会降低下游生成的质量。本文提出 AdaGReS，一个面向令牌预算 RAG 的冗余感知上下文选择框架，它优化了一个结合查询-块相关性与集合内冗余惩罚的集合级目标函数。AdaGGReS 在令牌预算约束下，利用从目标函数导出的边际增益执行贪婪选择，并引入一种闭式的、实例自适应的相关性与冗余权衡参数校准方法，以消除手动调参需求，并自适应候选池统计特征与预算限制。我们进一步提供了理论分析，表明在实用的嵌入相似性条件下，所提出的目标函数展现出 ε-近似次模性，从而为贪婪选择提供了近似最优性保证。在开放域问答（Natural Questions）和一个高冗余生物医学（药物）语料库上的实验表明，该方法在冗余控制和上下文质量方面均取得了一致的改进，并转化为更好的端到端答案质量及跨设置鲁棒性。