ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “Knowledge of language models and memory retrieval”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.IRcs.AIcs.MARecentMay 30, 2026

MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation

Chuanjie Wu, Zhishang Xiang, Yunbo Tang, Zerui Chen +2 more

MemGraphRAG introduces a novel memory-based multi-agent system to construct globally consistent and structurally sound knowledge graphs, significantly improving retrieval-augmented generation for comp…

View →
cs.IRcs.AIcs.CLEmpiricalRecentJun 12, 2026

Knowledge Graph Enhanced Memory-Augmented Retrieval for Long Context Modeling

Ghadir Alselwi, Basem Suleiman, Hao Xue, Shoaib Jameel +3 more

This paper introduces KGERMAR, a framework that constructs dynamic, context-specific knowledge graphs during inference for long-context language modeling, achieving lower perplexity and better memory…

View →
cs.IREmpiricalRecentOct 30, 2026

KITE: Retrieval as a Decision Procedure for Long-Term Conversational Memory

Feng Li, Kailun Tan, Zhibo Zhou, Youxiang Wang +4 more

This paper introduces KITE, a vector-free framework for memory retrieval in LLM agents that formulates memory retrieval as an explicit decision procedure.

View →
cs.AIcs.NETheoreticalRecentAug 16, 2026

Mental Model Management: An Operator-Based Framework for LLM Memory

Oliver Kramer

The paper introduces Mental Model Management (3M), a framework for representing knowledge as compact mental models and continuously integrating new information.

View →
cs.CLcs.AIcs.LGRecentMay 27, 2026

MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models

Hyeonjeong Ha, Jeonghwan Kim, Cheng Qian, Jiayu Liu +6 more

MemGuard introduces a type-aware memory framework to prevent heterogeneous memory contamination in long-term memory-augmented LLMs, significantly improving memory reliability and efficiency.

View →
cs.CLcs.AIEmpiricalRecentJul 23, 2026

RUMBA: Russian User Memory Benchmark

Elizaveta Shevtsova, Inna Glebkina, Mark Baushenko, Pavel Gulyaev +1 more

The paper introduces RUMBA, a new benchmark for long-term conversational memory in LLMs with a fine-grained taxonomy and unified methodology.

View →
cs.LGcs.AIcs.CLEmpiricalRecentJul 10, 2026

Remembering Distinct Items, Not Tokens: A Learnable Dirichlet-Process Cache Between State-Space Models and Attention

Siddharth Pal, Viktoria Rojkova

This paper proposes a sparse cache with a novel allocation rule based on DP-means clustering for deep recurrent models, achieving full associative recall with only distinct items, outperforming other…

View →
cs.CLcs.IREmpiricalRecentJun 9, 2026

ConvMemory v2: A Recall-Preserving Top-10 Evidence Reranker for Conversational Memory Retrieval

Taiheng Pan

This paper introduces ConvMemory v2, an opt-in token-evidence reranker that improves conversational memory retrieval performance.

View →
cs.CLSurveyRecentJul 1, 2026

Understanding Large Language Models

Yannik Keller, Thomas Eisenmann

This paper discusses the current understanding of Large Language Models (LLMs), their capabilities, and their relationship to human cognition, with a focus on emerging capabilities and mechanistic imp…

View →
cs.DScs.AIcs.CLRecentMay 28, 2026

On Language Generation in the Limit with Bounded Memory

Jon Kleinberg, Anay Mehrotra, Amin Saberi, Grigoris Velegkas

The paper analyzes language generation and identification in the limit under bounded memory, showing that memory constraints significantly alter learnability, particularly affecting achievable density…

View →
cs.CLcs.AIcs.IREmpiricalRecentOct 20, 2026

Factual Access States in Diffusion Language Models: From Mechanism to Knowledge Editing and Retrieval

Yuchen Guo, Zhuoyuan Mao, Yiwen Guo

This paper introduces a new framework for understanding how autoregressive and masked diffusion language models access factual knowledge.

View →
cs.AIRecentMay 28, 2026

VikingMem: A Memory Base Management System for Stateful LLM-based Applications

Jiajie Fu, Junwen Chen, Mengzhao Wang, Aoxiang He +4 more

The paper introduces VikingMem, a novel Memory Base Management System that effectively manages the persistent state of long-term LLM interactions by selectively extracting, evolving, and compressing m…

View →
cs.IRcs.CLEmpiricalRecentJul 9, 2026

Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging

Ahmed Rayane Kebir, Jose G. Moreno, Lynda Tamine

This paper introduces model merging as a training-free strategy for designing a single retrieval model that operates across both ad-hoc and conversational settings, improving ad-hoc search capabilitie…

View →
cs.CLcs.AIRecentMay 28, 2026

Unlocking the Working Memory of Large Language Models for Latent Reasoning

Lukas Aichberger, Sepp Hochreiter

The paper introduces Reasoning in Memory (RiM), a latent reasoning method that replaces autoregressive token generation with fixed memory blocks to enable compute-efficient internal working memory for…

View →
cs.CLcs.IREmpiricalRecentJun 10, 2026

uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking

Simon Lupart, Kidist Amde Mekonnen, Zahra Abbasiantaeb, Mohammad Aliannejadi

This paper proposes a multi-turn retrieval-augmented generation pipeline for conversational systems across four domains.

View →
cs.AIEmpiricalRecentOct 16, 2026

From Memory Hits to Answerable Evidence: Query-Conditioned Memory Compilation for Long-Term Agent Memory

Shangze Li, Yanyu Yao, Derong Xu, Zhi Zheng +1 more

This paper proposes MemCompile, a query-conditioned evidence compilation framework for long-term conversational memory.

View →
cs.AIcs.CLRecentMay 27, 2026

MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents

Zihan Li, Xingyu Fan, Feifei Li, Wenhui Que

The paper introduces MemCog, a Memory-as-Cognition system that integrates memory access directly into the reasoning process, significantly improving agent performance, especially in proactive memory r…

View →
cs.AIEmpiricalRecentJul 2, 2026

ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning

Yanjun Zhao, Ruizhong Qiu, Tianxin Wei, Yuanchen Bei +5 more

This paper proposes RECONTEXT, a training-free inference method for improving long-context reasoning in large language models using model-internal relevance signals and recursive evidence replay.

View →