ACL Findings2026
RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents
Zijie Dai, Shiyuan Deng, Sheng Guan, Yizhou Tian, Xin Yao, Xiao Yan, James Cheng
Abstract
Memory systems often organize user-agent interactions as retrievable external memory and are crucial for long-running agents by overcoming the limited context windows of LLMs. However, existing memory systems invoke LLMs to process every incoming interaction for memory extraction, and such an eager memory consolidation scheme leads to substantial token consumption. To tackle this problem, we propose RecMem by rethinking when memory consolidation should be conducted. RecMem stores incoming interactions in a subconscious memory layer and encode them using lightweight embedding models for retrieval. LLMs are only invoked to extract episodic and semantic memory when sustained recurrence are observed for semantically similar interactions. Such recurrence-based consolidation works because these interactions correspond to a semantic cluster with rich information and thus are worth extraction and summarization. To improve accuracy, RecMem also incorporates a semantic refinement mechanism that recovers the fine-grained facts omitted by memory extraction. Experiments show that RecMem reduces the memory construction token cost of three SOTA memory systems by up to 87% while exceeding their accuracy.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning cites MemoryBank: Enhancing Large Language Models with Long-Term Memory
- Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning cites A-Mem: Agentic Memory for LLM Agents
- Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions cites A-Mem: Agentic Memory for LLM Agents
- A-Mem: Agentic Memory for LLM Agents cites MemoryBank: Enhancing Large Language Models with Long-Term Memory
- A-Mem: Agentic Memory for LLM Agents cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Builds on10
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- A-Mem: Agentic Memory for LLM AgentsWujiang Xu, Zujie Liang, Kai Mei, Hang Gao et al.NeurIPS 2025 · 1,138 citations
- MemoryBank: Enhancing Large Language Models with Long-Term MemoryWanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye et al.AAAI 2024 · 394 citations
- Evaluating Memory in LLM Agents via Incremental Multi-Turn InteractionsYuanzhe Hu, Yu Wang, Julian McAuleyICLR 2026 · 246 citations
- Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement LearningSikuan Yan, Xiufeng Yang, Zuchao Huang, Ercong Nie et al.ACL 2026 · 140 citations
Related papers
- Lightweight LLM Agent Memory with Small Language ModelsJiaquan Zhang, Chaoning Zhang, Shuxu Chen, Zhenzhen Huang et al.ACL 2026 · 4 citations
- RGMem: Renormalization Group–inspired Memory Evolution for Language AgentsAo Tian, Yunfeng Lu, Xinxin Fan, Changhao Wang et al.ICML 2026 · 2 citations
- EMA: An Episodic Memory Agent for Efficient and Selective MemoryHongyi Lan, Jiaqi Song, Zhengjia Zhong, Hui Li et al.ACL Findings 2026
- EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon ReasoningChuanrui Hu, Xingze Gao, Zuyi Zhou, Dannong Xu et al.ACL 2026 · 26 citations
- CLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model AgentsTaeyun Roh, Wonjune Jang, Junha Jung, Jaewoo KangACL Findings 2026
