paper-with-me

Papers

LightMem: Lightweight and Efficient Memory-Augmented Generation

2025-10-21 · Jizhan Fang, Xinle Deng, Haoming Xu, Ziyan Jiang, Yuqi Tang, Ziwen Xu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Huajun Chen, Ningyu Zhang arxiv

Despite their remarkable capabilities, Large Language Models (LLMs) struggle to effectively leverage historical interaction information in dynamic and complex environments. Memory systems enable LLMs to move beyond stateless interactions by introducing persistent information storage, retrieval, and utilization mechanisms. However, existing memory systems often introduce substantial time and computational overhead. To this end, we introduce a new memory system called LightMem, which strikes a balance between the performance and efficiency of memory systems. Inspired by the Atkinson-Shiffrin model of human memory, LightMem organizes memory into three complementary stages. First, cognition-inspired sensory memory rapidly filters irrelevant information through lightweight compression and groups information according to their topics. Next, topic-aware short-term memory consolidates these topic-based groups, organizing and summarizing content for more structured access. Finally, long-term memory with sleep-time update employs an offline procedure that decouples consolidation from online inference. On LongMemEval and LoCoMo, using GPT and Qwen backbones, LightMem consistently surpasses strong baselines, improving QA accuracy by up to 7.7% / 29.3%, reducing total token usage by up to 38x / 20.9x and API calls by up to 30x / 55.5x, while purely online test-time costs are even lower, achieving up to 106x / 117x token reduction and 159x / 310x fewer API calls. The code is available at https://github.com/zjunlp/LightMem.

📄 PDF Abstract BibTeX arXiv:2510.18866

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

LightMem-Ego: Your AI Memory for Everyday Life

2026-07-13 · Yijun Chen, Boyi Xiao, Yixian Zhao, Haoting Xia 외 hf

Personal AI assistants on mobile and wearable devices continuously perceive users' daily lives through visual and audio streams. However, answering queries about past experiences requires lightweight multimodal memory th…

Lightweight LLM Agent Memory with Small Language Models

2026-04-09 · Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Zhenzhen Huang 외 arxiv

Although LLM agents can leverage tools for complex tasks, they still need memory to maintain cross-turn consistency and accumulate reusable information in long-horizon interactions. However, retrieval-based external memo…

DimMem: Dimensional Structuring for Efficient Long-Term Agent Memory

2026-05-15 · Wentao Qiu, Haotian Hu, Fanyi Wang, Jinwei Kong 외 arxiv

Large language model (LLM) agents require long-term memory to leverage information from past interactions. However, existing memory systems often face a fidelity--efficiency trade-off: raw dialogue histories are expensiv…

Rethinking Memory as Continuously Evolving Connectivity

2026-05-27 · Jizhan Fang, Buqiang Xu, Zhixian Wang, Haoliang Cao 외 arxiv

Existing memory-augmented LLM agents often treat memory as a static repository with pre-defined representations and fixed retrieval pipelines, which is brittle in dynamic agentic environments where feedback, task variati…

EM^2Mem: Event-Centric Multimodal Memory for Large Language Models

2026-09-01 · Yijun Chen, Yaqi Zheng, Yanya Li, Boyi Xiao 외 hf

Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve captions, frames, transcripts, summaries, or graph facts as isolated fragments. Although searchable, su…

Video Question Answering