# Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-k

arXiv: https://arxiv.org/abs/2506.08479 · HTML: https://mlsanity.com/paper/2506.08479/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 20 of its 26 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 20 of 20)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [∞Bench: Extending Long Context Evaluation Beyond 100K Tokens](https://mlsanity.com/paper/2402.13718/) (2024)
- [RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation](https://mlsanity.com/paper/2404.00610/) (2024)
- [HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly](https://mlsanity.com/paper/2410.02694/) (2024)
- [Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG](https://mlsanity.com/paper/2410.05983/) (2024)
- [Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach](https://mlsanity.com/paper/2407.16833/) (2024)
- [Searching for Best Practices in Retrieval-Augmented Generation](https://mlsanity.com/paper/2407.01219/) (2024)
- [In Defense of RAG in the Era of Long-Context Language Models](https://mlsanity.com/paper/2409.01666/) (2024)
- [Long Context vs. RAG for LLMs: An Evaluation and Revisits](https://mlsanity.com/paper/2501.01880/) (2024)
- [The Price of Prompting: Profiling Energy Use in Large Language Models Inference](https://mlsanity.com/paper/2407.16893/) (2024)
- [Are Long-LLMs A Necessity For Long-Context Tasks?](https://mlsanity.com/paper/2405.15318/) (2024)
- [Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data](https://mlsanity.com/paper/2410.11996/) (2024)
- [Retrieval Or Holistic Understanding? Dolce: Differentiate Our Long Context Evaluation Tasks](https://mlsanity.com/paper/2409.06338/) (2024)

## Built on by (most cited first, 21 of 21)

- [How Many Tools Should an LLM Agent See? A Chance-Corrected Answer](https://mlsanity.com/paper/2605.24660/) (2026)
- [MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedback](https://mlsanity.com/paper/2606.07909/) (2026)
- [Replace, Don't Expand: Mitigating Context Dilution in Multi-Hop RAG via Fixed-Budget Evidence Assembly](https://mlsanity.com/paper/2512.10787/) (2025)
- [Dynamic Context Selection for Retrieval-Augmented Generation: Mitigating Distractors and Positional Bias](https://mlsanity.com/paper/2512.14313/) (2025)
- [Align Then Adapt: Label-Efficient Adapter Learning for Asymmetric Dense Retrieval](https://mlsanity.com/paper/2604.03403/) (2026)
- [MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking](https://mlsanity.com/paper/2607.17751/) (2026)
- [SAGE: SLO-Aware Adaptive Retrieval for Production RAG Systems](https://mlsanity.com/paper/2608.08237/) (2026)
- [Noesis: Bidirectional Graph-RAG with Adaptive Parallelism and Cross-Knowledge-Base Semantic Discovery](https://mlsanity.com/paper/2608.15919/) (2026)
- [Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgeting](https://mlsanity.com/paper/2608.25115/) (2026)
- [ViSAR: Training-Free Adaptive-k Retrieval for Visual Document Question Answering](https://mlsanity.com/paper/2609.02486/) (2026)
- [Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge Grounding](https://mlsanity.com/paper/2509.21865/) (2025)
- [Context-Picker: Dynamic context selection using multi-stage reinforcement learning](https://mlsanity.com/paper/2512.14465/) (2025)
- [AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented Generation](https://mlsanity.com/paper/2605.05245/) (2026)
- [GRASP: Graph Agentic Search over Propositions for Multi-hop Question Answering](https://mlsanity.com/paper/2605.16598/) (2026)
- [EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering](https://mlsanity.com/paper/2606.06906/) (2026)
- [Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation](https://mlsanity.com/paper/2606.11907/) (2026)
- [D2-ScaleAgent: Dual-Dimensional Scaling for Long Document Understanding](https://mlsanity.com/paper/2608.16417/) (2026)
- [PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations](https://mlsanity.com/paper/2609.09664/) (2026)
- [BELIEFRAG: Making Adaptive RAG State-Aware under Evolving Evidence](https://mlsanity.com/paper/2609.39139/) (2026)
- [SEEDS: Preview-Guided Evidence Admission for Search Agents](https://mlsanity.com/paper/2610.12932/) (2026)
- [SuPER-Mamba: Surprisal Prioritization for Extended-Context Routing in Mamba](https://mlsanity.com/paper/2610.16636/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) and long-context language models (LCLMs) both address context limitations of LLMs in open-domain question answering (QA). However, optimal external context to retrieve remains an open problem: fixing the retrieval size risks either wasting tokens or omitting key evidence. Existing adaptive methods like Self-RAG and Self-Route rely on iterative LLM prompting and perform well on factoid QA, but struggle with aggregation QA, where the optimal context size is both unknown and variable. We present Adaptive-k retrieval, a simple and effective single-pass method that adaptively selects the number of passages based on the distribution of the similarity scores between the query and the candidate passages. It does not require model fine-tuning, extra LLM inferences or changes to existing retriever-reader pipelines. On both factoid and aggregation QA benchmarks, Adaptive-k matches or outperforms fixed-k baselines while using up to 10x fewer tokens than full-context input, yet still retrieves 70% of relevant passages. It improves accuracy across five LCLMs and two embedding models, highlighting that dynamically adjusting context size leads to more efficient and accurate QA.