Agent Zero Memory is a provenance‑aware long‑term memory system for large language model agents that distills user interactions into three parallel memory structures: an episodic timeline, an associative entity‑event knowledge graph, and a semantic, citation‑locked hierarchical documentary memory. Retrieval is performed via an intent gate, source router, and concurrent searches across the three systems, producing integrated, cited answers that exclude fabrication and require evidence the reader has opened. The system achieves state‑of‑the‑art performance on LongMemEval (95.60%) and LoCoMo (93.60%) while offering a favorable accuracy‑cost‑latency trade‑off across multiple backbone LLMs.
By Ming Wu, Pengyuan Zhu
The paper introduces StructMemEval, a benchmark designed to assess how well large language model (LLM) agents can organize their long‑term memory rather than merely recall facts. It compiles tasks that humans typically solve by structuring knowledge—such as transaction ledgers, to‑do lists, and trees—and evaluates agents on these. Experiments show that simple retrieval‑augmented LLMs struggle with such organization tasks, while memory‑augmented agents perform better when explicitly prompted to structure their memory, yet many modern LLMs still fail to recognize memory structures without prompting.
By Alina Shutova, Alexandra Olenina, Ivan Vinogradov, Anton Sinitsin
The paper introduces AMA, a framework that uses multiple agents—Constructor, Retriever, Judge, and Refresher—to manage memory for large language model agents. AMA’s hierarchical memory design dynamically adjusts retrieval granularity to match task complexity, while the Judge and Refresher ensure relevance, consistency, and timely updates. Experiments on long-context benchmarks show AMA outperforms existing baselines and cuts token usage by about 80% compared to full-context approaches.
By Weiquan Huang, Zixuan Wang, Hehai Lin, Sudong Wang, Bo Xu, Qian Li, Beier Zhu, Linyi Yang, Chengwei Qin
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)
EnSIMem is an entity‑structured long‑term memory architecture designed for agents that interact with users over extended periods. It organizes interactions into theme‑coherent episodes and creates dialogue‑grounded index entries of the form [entity][entity type][property:value], preserving source turns, temporal data, and multimodal fields. During online interaction, the agent decomposes requests into evidence requirements, performs entity‑property lookup, and retrieves the necessary evidence to generate responses directly from preserved source material rather than lossy summaries.
By Xuanyu Meng, Xing Fan, Xinyi Fan, Chenlei Guo, Yixuan Xie, Jiawei Han
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
arXiv:2607. 26520v1 Announce Type: cross Abstract: Conversational AI agents commonly lack persistent memory across sessions.
By Alp Niksarli, Gopesh Baheti
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
An agent that interacts with users over long periods must recall facts, preferences, events, and changes from a continuously growing interaction history. Existing memory systems often compress interac...
The paper introduces MERIT, a benchmark that evaluates the marginal benefit of long‑term memory for tool‑using large language model agents while explicitly accounting for cost. MERIT provides episodic tool‑use tasks across three domains, verifies dependence on earlier‑episode facts, and measures memory operations in tokens and dollars. Experiments on GPT‑4.1‑mini, Claude Haiku 4.5, and Claude Sonnet 5 show that memory can significantly improve task success, but its utility varies widely across models and memory implementations, and full replay is rarely cost‑effective.
By Shweta Mishra, Shashank Mishra
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
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