Image de couverture de livre

Structured Distillation for Personalized Agent Memory: 11x Token Reduction with Retrieval Preservation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Lewis, Sydney
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence Computation and Language Information Retrieval
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
par: Cheng, Xin, et autres
Publié: (2024)

SPIRE: Structure-Preserving Interpretable Retrieval of Evidence
par: Rainey, Mike, et autres
Publié: (2026)

PerLTQA: A Personal Long-Term Memory Dataset for Memory Classification, Retrieval, and Synthesis in Question Answering
par: Du, Yiming, et autres
Publié: (2024)

Distillation Enhanced Generative Retrieval
par: Li, Yongqi, et autres
Publié: (2024)

ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents
par: Zhang, Xiaohui, et autres
Publié: (2026)

Pctx: Tokenizing Personalized Context for Generative Recommendation
par: Zhong, Qiyong, et autres
Publié: (2025)

A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
par: Xu, Shicheng, et autres
Publié: (2024)

Towards Lossless Token Pruning in Late-Interaction Retrieval Models
par: Zong, Yuxuan, et autres
Publié: (2025)

Semi-Parametric Retrieval via Binary Bag-of-Tokens Index
par: Zhou, Jiawei, et autres
Publié: (2024)

Learning to Reason for Multi-Step Retrieval of Personal Context in Personalized Question Answering
par: Amirizaniani, Maryam, et autres
Publié: (2026)

MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens
par: Chen, Yu, et autres
Publié: (2026)

SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems
par: Bhardwaj, Varun Pratap
Publié: (2026)

Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs
par: Tavakoli, Mohammad, et autres
Publié: (2025)

FinRetrieval: A Benchmark for Financial Data Retrieval by AI Agents
par: Kim, Eric Y., et autres
Publié: (2026)

MultiContrievers: Analysis of Dense Retrieval Representations
par: Goldfarb-Tarrant, Seraphina, et autres
Publié: (2024)

Learning to Retrieve from Agent Trajectories
par: Zhou, Yuqi, et autres
Publié: (2026)

Thinking Ahead: Prospection-Guided Retrieval of Memory with Language Models
par: Chopra, Harshita, et autres
Publié: (2026)

Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling
par: Clavié, Benjamin, et autres
Publié: (2024)

Large Language Models Empowered Personalized Web Agents
par: Cai, Hongru, et autres
Publié: (2024)

ClusterRAG: Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation
par: Nkhata, Gibson, et autres
Publié: (2026)

Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
par: Sun, Yiqun, et autres
Publié: (2026)

Zep: A Temporal Knowledge Graph Architecture for Agent Memory
par: Rasmussen, Preston, et autres
Publié: (2025)

GeAR: Graph-enhanced Agent for Retrieval-augmented Generation
par: Shen, Zhili, et autres
Publié: (2024)

TURA: Tool-Augmented Unified Retrieval Agent for AI Search
par: Zhao, Zhejun, et autres
Publié: (2025)

Memory-Based vs. Context-Only Conditioning Produces Distinct Behavioral Patterns in Stateful Personalization
par: Park, Junsoo, et autres
Publié: (2026)

Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information
par: Zhang, Zeyu, et autres
Publié: (2025)

Bias-Aware Agent: Enhancing Fairness in AI-Driven Knowledge Retrieval
par: Singh, Karanbir, et autres
Publié: (2025)

PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
par: Yang, Ke, et autres
Publié: (2026)

MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents
par: Zhou, Zijian, et autres
Publié: (2025)

A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
par: Lee, Kuang-Huei, et autres
Publié: (2024)

TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision
par: Zhou, Ruiwen, et autres
Publié: (2024)

Lab-AI: Using Retrieval Augmentation to Enhance Language Models for Personalized Lab Test Interpretation in Clinical Medicine
par: Wang, Xiaoyu, et autres
Publié: (2024)

TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendation
par: Qu, Haohao, et autres
Publié: (2024)

DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval
par: Sun, Maojun, et autres
Publié: (2026)

One Model Is Enough: Native Retrieval Embeddings from LLM Agent Hidden States
par: Jiang, Bo
Publié: (2026)

Understanding Inequality of LLM Fact-Checking over Geographic Regions with Agent and Retrieval models
par: Coelho, Bruno, et autres
Publié: (2025)

FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering
par: Choi, Chanyeol, et autres
Publié: (2025)

AgentMaster: A Multi-Agent Conversational Framework Using A2A and MCP Protocols for Multimodal Information Retrieval and Analysis
par: Liao, Callie C., et autres
Publié: (2025)

Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledge
par: Boer, Derian, et autres
Publié: (2025)

Use of Retrieval-Augmented Large Language Model Agent for Long-Form COVID-19 Fact-Checking
par: Huang, Jingyi, et autres
Publié: (2025)