arXiv AI July 21, 2026 By Zicheng Zhao, Xinyang Guo, Luyao Lv, Menghan Wang, Ming Li, Shuaicheng Li

Accurate and Efficient Long-Term Memory for LLM Agents

arXiv:2607. 16211v1 Announce Type: new Abstract: LLM agents augmented with persistent memory can recall past interactions, but existing systems suffer from two limitations: flat, unstructured storage loses relational context needed for multi-hop and temporal reasoning, and reliance on expensive LLM-based classification makes them impractical for latency-sensitive deployment.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 30

Mandol: An Agglomerative Agent Memory System for Long-Term Conversations

arXiv:2606. 29778v1 Announce Type: cross Abstract: Long-term conversational agents need to remember and query cross-session, multi-typed information with complex correlations.

By Yuhan Zhang (Institute of Software, Chinese Academy of Sciences), Zhiyuan Guo (Institute of Software, Chinese Academy of Sciences), Ziheng Zeng (Institute of Software, Chinese Academy of Sciences), Wei Wang (Institute of Software, Chinese Academy of Sciences), Wentao Wu (Microsoft Research), Lijie Xu (Institute of Software, Chinese Academy of Sciences)

llms rag agents benchmarks

arXiv AI

Aug 6

Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite

arXiv:2608. 05095v1 Announce Type: new Abstract: Agents for long term reasoning require a memory that can be efficiently and effectively updated over time, as new facts and external feedback continue to arrive.

By Xiawei Yue, Boran Wang, Xiaoqing Zhang, Shuxin Zheng, Ziwei Zhang

llms agents nlp benchmarks

arXiv AI

Jul 31

A Graph-Native Bitemporal Memory Store for Conversational AI Agents

arXiv:2607. 26520v1 Announce Type: cross Abstract: Conversational AI agents commonly lack persistent memory across sessions.

By Alp Niksarli, Gopesh Baheti

llms rag agents benchmarks

arXiv AI

Jun 30

Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions

arXiv:2507. 05257v4 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents primarily focus on evaluating reasoning, planning, and execution capabilities, while another critical component-memory, encompassing how agents memorize, update, and retrieve long-term information-is under-evaluated due to the lack of benchmarks.

By Yuanzhe Hu, Yu Wang, Julian McAuley

llms rag agents benchmarks

arXiv AI

Jun 10

Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full History

arXiv:2606. 09900v1 Announce Type: cross Abstract: Long-term memory is the missing layer for LLM agents: across sessions they forget, and the common workaround -- replaying the whole history into the prompt -- is expensive, slow, and, as distractors accumulate, less accurate.

By Liuyin Wang

llms agents benchmarks

arXiv AI

Jul 31

IFCMemoryBench: Evaluating Long-Term Memory of LLM-Based Agents in BIM Information Retrieval

arXiv:2607. 26072v1 Announce Type: cross Abstract: Long-term memory is becoming a core capability of LLM-based agents, but existing evaluations largely test conversational recall in open-domain or persona-grounded settings.

By Changyu Du, Alexander Vosseler, Filippo Mazza, Andr\'e Borrmann

llms agents benchmarks

Related stories

Mandol: An Agglomerative Agent Memory System for Long-Term Conversations

Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite

A Graph-Native Bitemporal Memory Store for Conversational AI Agents

Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions

Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full History

IFCMemoryBench: Evaluating Long-Term Memory of LLM-Based Agents in BIM Information Retrieval