New papers propose memory systems for LLM agents

Arxiv CS.CL (NLP/language models)

At least 11 papers from June 2026 on arXiv introduce memory frameworks for long-running LLM agents, including G-Long, MemRefine, and Infini Memory. They address statelessness and context-window limits with hierarchical retrieval, compression, and topic-based storage.

LLMMemory

See 10 more sources

MemRefine: LLM-Guided Compression for Long-Term Agent Memory2 days agoMinjae Kim, Jinheon Baek, Soyeong Jeong, Sung Ju Hwang

Learning What to Remember: A Cognitively Grounded Multi-Factor Value Model for Agentic Memory2 days agoZhibao Chen, Qian Cheng

Substrate Asymmetry in User-Side Memory: A Diagnostic Framework3 days agoYouwang Deng

Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents3 days agoHao-Lun Hsu, Nikki Lijing Kuang, Boyi Liu, Zhewei Yao, Yuxiong He

PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents3 days agoRipon Chandra Malo, Tong Qiu

WebChallenger: A Reliable and Efficient Generalist Web Agent4 days agoJayoo Hwang, Xiaowen Zhang, Vedant Padwal

Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory4 days agoSuozhao Ji, Baodong Wu, Zehao Wang, Lei Xia, Qingping Li, Ruisong Wang, Wenbo Ding, Zhenhua Zhu, Boxun Li, Guohao Dai, Yu Wang

Deployment-Time Memorization in Foundation-Model Agents4 days agoLei (Rachel), Chen, Guilin Zhang, Kai Zhao, Dalmo Cirne, Andy Olsen, Xu Chu, Zeke Miller, Alet Blanken, Amine Anoun, Jerry Ting

Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full History4 days agoLiuyin Wang

AdMem: Advanced Memory for Task-solving Agents6 days agoRunzhe Wang, Huilin Lu, Shengjie Liu, Li Dong, Jason Zhu

Arxiv CS.CL (NLP/language models)·Minjun ChoiYoonjin JangSangwon YounYoungjoong Ko

2 days ago