New benchmarks and memory systems for long-horizon AI agents

Arxiv CS.AI (top papers)

A wave of 12 new papers in June 2026 propose memory architectures and benchmarks for long-horizon LLM agents. Systems like AdMem and AdaMEM introduce persistent and adaptive memory, while benchmarks like SentinelBench and SubtleMemory evaluate long-running and memory discrimination capabilities.

memoryllm

See 14 more sources

Give your AI agent its own computer5 days ago

Gives every AI agent its own desktop, network, and memory3 days agoTom Doerr

Persistent working memory for OpenCode agents13 days agoTom Doerr

Persistent memory for OpenCode AI coding agents2 days agoTom Doerr

Orchestrates self-hosted AI agent swarms with durable memory9 hours agoTom Doerr

Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory23 hours agoSuozhao Ji, Baodong Wu, Zehao Wang, Lei Xia, Qingping Li, Ruisong Wang, Wenbo Ding, Zhenhua Zhu, Boxun Li, Guohao Dai, Yu Wang

ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning23 hours agoYunhan Jiang, Wenbin Duan, Shasha Guo, Liang Pang, Xiaoqian Sun, Huawei Shen

Deployment-Time Memorization in Foundation-Model Agents23 hours agoLei (Rachel), Chen, Guilin Zhang, Kai Zhao, Dalmo Cirne, Andy Olsen, Xu Chu, Zeke Miller, Alet Blanken, Amine Anoun, Jerry Ting

MemToolAgent overview with a simple restaurant booking scenario where the agent retrieves similar memories, receives feedback on an invalid time format, and generates a reflection to update its memory2 days agoSuleyman Armagan Er, Danilo Ribeiro, Yogesh Virkar, Surafel Lakew, Adi Kalyanpur, James Gung, Thomas Delteil, Arshit Gupta

Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents23 hours agoQingcan Kang, Liu Mingyang, Shixiong Kai, Kaichao Liang, Tao Zhong, Mingxuan Yuan

MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution2 days agoBowen Ren, Heyan Huang, Yinghao Li, Yang Gao

Tree-of-Experience: A Structured Experience-Management Solution for Self-Evolving Agents under Low-Repetition and Implicit-Reward Environments3 days agoZihao Deng, Yining Zhu, Leiming Wang, Jingfei Lu, Junbo Wang, Chuncheng Ran, Yu Yang, Dixuan Yang, Jikun Shen

Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution23 hours agoXucong Wang, Ziyu Ma, Shidong Yang, Tongwen Huang, Pengkun Wang, Yong Wang, Xiangxiang Chu

OpenSkill: Open-World Self-Evolution for LLM Agents2 days agoZhiling Yan, Dingjie Song, Hanrong Zhang, Wei Liang, Yuxuan Zhang, Yutong Dai, Lifang He, Philip S. Yu, Ran Xu, Xiang Li, Lichao Sun

Arxiv CS.AI (top papers)·Xinyu GuanQianyang ZhaoYuming Deng

3 days ago