# Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgeting

arXiv: https://arxiv.org/abs/2608.25115 · HTML: https://mlsanity.com/paper/2608.25115/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation.
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)
- Efficient LLM inference and serving / [Prompt and context compression](https://mlsanity.com/inference/prompt-and-context-compression/)

## Builds on (most cited first, 29 of 29)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://mlsanity.com/paper/2003.06713/) (2020)
- [RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation](https://mlsanity.com/paper/2310.04408/) (2023)
- [RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs](https://mlsanity.com/paper/2407.02485/) (2024)
- [Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval](https://mlsanity.com/paper/2009.12756/) (2020)
- [SPLADE-v3: New baselines for SPLADE](https://mlsanity.com/paper/2403.06789/) (2024)
- [Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval](https://mlsanity.com/paper/2101.00436/) (2021)
- [Provence: efficient and robust context pruning for retrieval-augmented generation](https://mlsanity.com/paper/2501.16214/) (2025)
- [Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-k](https://mlsanity.com/paper/2506.08479/) (2025)
- [A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADE](https://mlsanity.com/paper/2403.10407/) (2024)
- [METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation](https://mlsanity.com/paper/2412.10543/) (2024)
- [Better RAG using Relevant Information Gain](https://mlsanity.com/paper/2407.12101/) (2024)
- [HyperRAG: Enhancing Quality-Efficiency Tradeoffs in Retrieval-Augmented Generation with Reranker KV-Cache Reuse](https://mlsanity.com/paper/2504.02921/) (2025)
- [Efficient Listwise Reranking with Compressed Document Representations](https://mlsanity.com/paper/2604.26483/) (2026)

## Built on by (most cited first, 1 of 1)

- [The Missing Complement: State-Conditioned Minimal Sufficient Evidence for Coding Agents](https://mlsanity.com/paper/2609.20050/) (2026)

## Abstract (arXiv)

Existing methods for improving Retrieval-Augmented Generation (RAG) efficiency mainly optimize downstream LLM generation, such as context compression or serving optimization. However, RAG is an end-to-end system, and its bottleneck can shift between upstream reranking and downstream generation under different serving loads and reranking budgets.In this paper, we first empirically characterize this shifting-bottleneck behavior and show that upstream reranking can become the dominant bottleneck under high query rates or large reranking budgets. Reducing the reranking budget can relieve this bottleneck, but it may also drop supporting evidence and degrade recall. To address this problem, we propose textbftextsfPACE (Prioritized Adaptive Coverage of Evidence), a training-free framework that combines textitevidence frontloading with textitpressure-adaptive budgeting. textsfPACE first reorders candidates by marginal evidence coverage, prioritizing documents that are query-relevant, complementary, and useful for forming multi-hop evidence chains. We show that this objective is monotone submodular, giving greedy selection a (1-1/e) approximation guarantee. textsfPACE then dynamically adjusts the reranking budget according to the relative pressure of the reranker and the LLM. Experiments on three multi-hop QA datasets and online serving simulations show that textsfPACE improves evidence recall, reduces p95 latency under ranking-heavy workloads. More importantly, the two components together reveal that textitless can be more: an evidence-dense top-ranked candidates enable higher final recall with fewer reranked documents.