# CompAct: Compressing Retrieved Documents Actively for Question Answering

arXiv: https://arxiv.org/abs/2407.09014 · HTML: https://mlsanity.com/paper/2407.09014/

## Key facts

- Cited by 64 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 30 of its 49 references that are in the map.
- First posted on arXiv 12 Jul 2024.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 30 of 30)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [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)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [Learning to Compress Prompts with Gist Tokens](https://mlsanity.com/paper/2304.08467/) (2023)
- [Adapting Language Models to Compress Contexts](https://mlsanity.com/paper/2305.14788/) (2023)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://mlsanity.com/paper/2004.07347/) (2020)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [Knowledge Graph Prompting for Multi-Document Question Answering](https://mlsanity.com/paper/2308.11730/) (2023)
- [A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts](https://mlsanity.com/paper/2402.09727/) (2024)
- [Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading](https://mlsanity.com/paper/2310.05029/) (2023)
- [xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token](https://mlsanity.com/paper/2405.13792/) (2024)
- [Make Your LLM Fully Utilize the Context](https://mlsanity.com/paper/2404.16811/) (2024)
- [Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs](https://mlsanity.com/paper/2406.02376/) (2024)
- [Are Long-LLMs A Necessity For Long-Context Tasks?](https://mlsanity.com/paper/2405.15318/) (2024)

## Built on by (most cited first, 30 of 64)

- [MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents](https://mlsanity.com/paper/2506.15841/) (2025)
- [Prompt Compression for Large Language Models: A Survey](https://mlsanity.com/paper/2410.12388/) (2024)
- [Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models](https://mlsanity.com/paper/2410.07176/) (2024)
- [A Survey of Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.08748/) (2025)
- [Provence: efficient and robust context pruning for retrieval-augmented generation](https://mlsanity.com/paper/2501.16214/) (2025)
- [AgentOCR: Reimagining Agent History via Optical Self-Compression](https://mlsanity.com/paper/2601.04786/) (2026)
- [GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment](https://mlsanity.com/paper/2505.12215/) (2025)
- [EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.12559/) (2024)
- [Hierarchical Document Refinement for Long-context Retrieval-augmented Generation](https://mlsanity.com/paper/2505.10413/) (2025)
- [MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environments](https://mlsanity.com/paper/2510.01353/) (2025)
- [COMI: Coarse-to-fine Context Compression via Marginal Information Gain](https://mlsanity.com/paper/2602.01719/) (2026)
- [R3Mem: Bridging Memory Retention and Retrieval via Reversible Compression](https://mlsanity.com/paper/2502.15957/) (2025)
- [VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?](https://mlsanity.com/paper/2512.15649/) (2025)
- [SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression](https://mlsanity.com/paper/2507.05633/) (2025)
- [Read As Human: Compressing Context via Parallelizable Close Reading and Skimming](https://mlsanity.com/paper/2602.01840/) (2026)
- [AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees](https://mlsanity.com/paper/2512.04550/) (2025)
- [GORAG: Graph-based Online Retrieval Augmented Generation for Dynamic Few-shot Social Media Text Classification](https://mlsanity.com/paper/2501.02844/) (2025)
- [HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks](https://mlsanity.com/paper/2502.13465/) (2025)
- [SCOPE: A Generative Approach for LLM Prompt Compression](https://mlsanity.com/paper/2508.15813/) (2025)
- [Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression](https://mlsanity.com/paper/2602.08324/) (2026)
- [CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling](https://mlsanity.com/paper/2602.01766/) (2026)
- [Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation](https://mlsanity.com/paper/2409.12468/) (2024)
- [OSCAR: Online Soft Compression And Reranking](https://mlsanity.com/paper/2504.07109/) (2025)
- [ECoRAG: Evidentiality-guided Compression for Long Context RAG](https://mlsanity.com/paper/2506.05167/) (2025)
- [End-to-End Context Compression at Scale](https://mlsanity.com/paper/2606.09659/) (2026)
- [Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings](https://mlsanity.com/paper/2508.06030/) (2025)
- [AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation](https://mlsanity.com/paper/2509.17486/) (2025)
- [MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering](https://mlsanity.com/paper/2604.16313/) (2026)
- [Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Driven](https://mlsanity.com/paper/2605.09463/) (2026)
- [Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents](https://mlsanity.com/paper/2606.11680/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation supports language models to strengthen their factual groundings by providing external contexts. However, language models often face challenges when given extensive information, diminishing their effectiveness in solving questions. Context compression tackles this issue by filtering out irrelevant information, but current methods still struggle in realistic scenarios where crucial information cannot be captured with a single-step approach. To overcome this limitation, we introduce CompAct, a novel framework that employs an active strategy to condense extensive documents without losing key information. Our experiments demonstrate that CompAct brings significant improvements in both performance and compression rate on multi-hop question-answering benchmarks. CompAct flexibly operates as a cost-efficient plug-in module with various off-the-shelf retrievers or readers, achieving exceptionally high compression rates (47x).