Imagen de Portada

Boosting Long-Context Management via Query-Guided Activation Refilling

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Qian, Hongjin, Liu, Zheng, Zhang, Peitian, Dou, Zhicheng, Lian, Defu
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Artificial Intelligence Information Retrieval
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks
por: Qian, Hongjin, et al.
Publicado: (2025)

Grounding Language Model with Chunking-Free In-Context Retrieval
por: Qian, Hongjin, et al.
Publicado: (2024)

MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation
por: Qian, Hongjin, et al.
Publicado: (2024)

C-Pack: Packed Resources For General Chinese Embeddings
por: Xiao, Shitao, et al.
Publicado: (2023)

MetaAgent: Toward Self-Evolving Agent via Tool Meta-Learning
por: Qian, Hongjin, et al.
Publicado: (2025)

AssistRAG: Boosting the Potential of Large Language Models with an Intelligent Information Assistant
por: Zhou, Yujia, et al.
Publicado: (2024)

Model-Document Protocol for AI Search
por: Qian, Hongjin, et al.
Publicado: (2025)

From Matching to Generation: A Survey on Generative Information Retrieval
por: Li, Xiaoxi, et al.
Publicado: (2024)

Search-o1: Agentic Search-Enhanced Large Reasoning Models
por: Li, Xiaoxi, et al.
Publicado: (2025)

MemoBrain: Executive Memory as an Agentic Brain for Reasoning
por: Qian, Hongjin, et al.
Publicado: (2026)

HiRA: A Hierarchical Reasoning Framework for Decoupled Planning and Execution in Deep Search
por: Jin, Jiajie, et al.
Publicado: (2025)

Are Long-LLMs A Necessity For Long-Context Tasks?
por: Qian, Hongjin, et al.
Publicado: (2024)

WebThinker: Empowering Large Reasoning Models with Deep Research Capability
por: Li, Xiaoxi, et al.
Publicado: (2025)

Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
por: Zhou, Yujia, et al.
Publicado: (2024)

Long Context Compression with Activation Beacon
por: Zhang, Peitian, et al.
Publicado: (2024)

Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval
por: Lan, Junwei, et al.
Publicado: (2025)

Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism
por: Tang, Yimin, et al.
Publicado: (2024)

ProRAG: Process-Supervised Reinforcement Learning for Retrieval-Augmented Generation
por: Wang, Zhao, et al.
Publicado: (2026)

DeepXiv-SDK: An Agentic Data Interface for Scientific Literature
por: Qian, Hongjin, et al.
Publicado: (2026)

RGAlign-Rec: Ranking-Guided Alignment for Latent Query Reasoning in Recommendation Systems
por: Liu, Junhua, et al.
Publicado: (2026)

DEGAP: Dual Event-Guided Adaptive Prefixes for Templated-Based Event Argument Extraction with Slot Querying
por: Wang, Guanghui, et al.
Publicado: (2024)

FG-RAG: Enhancing Query-Focused Summarization with Context-Aware Fine-Grained Graph RAG
por: Hong, Yubin, et al.
Publicado: (2025)

General Agentic Memory Via Deep Research
por: Yan, B. Y., et al.
Publicado: (2025)

Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation
por: Li, Mufei, et al.
Publicado: (2025)

When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities
por: Chen, Jin, et al.
Publicado: (2023)

Self-Manager: Parallel Agent Loop for Long-form Deep Research
por: Xu, Yilong, et al.
Publicado: (2026)

Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation
por: Zhang, Chenghao, et al.
Publicado: (2025)

INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning
por: Zhu, Yutao, et al.
Publicado: (2024)

DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion
por: Mehta, Rahul, et al.
Publicado: (2026)

Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging
por: Qian, Hongjin, et al.
Publicado: (2025)

Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-$k$
por: Taguchi, Chihiro, et al.
Publicado: (2025)

RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation
por: Li, Xiaoxi, et al.
Publicado: (2024)

Little Giants: Synthesizing High-Quality Embedding Data at Scale
por: Chen, Haonan, et al.
Publicado: (2024)

SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
por: Jin, Yiqiao, et al.
Publicado: (2025)

GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval
por: Liu, Lingyuan, et al.
Publicado: (2025)

HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches
por: Tan, Jiejun, et al.
Publicado: (2025)

ECoRAG: Evidentiality-guided Compression for Long Context RAG
por: Jeong, Yeonseok, et al.
Publicado: (2025)

RedParrot: Accelerating NL-to-DSL for Business Analytics via Query Semantic Caching
por: Wang, Tong, et al.
Publicado: (2026)

A Semi-supervised Scalable Unified Framework for E-commerce Query Classification
por: Yuan, Chunyuan, et al.
Publicado: (2025)

You Only Use Reactive Attention Slice For Long Context Retrieval
por: Soh, Yun Joon, et al.
Publicado: (2024)