Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Ke, Chen, Zixi, He, Xuan, Jiang, Jize, Galley, Michel, Wang, Chenglong, Gao, Jianfeng, Han, Jiawei, Zhai, ChengXiang
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.03296
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917311607209984
author Yang, Ke
Chen, Zixi
He, Xuan
Jiang, Jize
Galley, Michel
Wang, Chenglong
Gao, Jianfeng
Han, Jiawei
Zhai, ChengXiang
author_facet Yang, Ke
Chen, Zixi
He, Xuan
Jiang, Jize
Galley, Michel
Wang, Chenglong
Gao, Jianfeng
Han, Jiawei
Zhai, ChengXiang
contents Long-term memory is essential for large language model (LLM) agents operating in complex environments, yet existing memory designs are either task-specific and non-transferable, or task-agnostic but less effective due to low task-relevance and context explosion from raw memory retrieval. We propose PlugMem, a task-agnostic plugin memory module that can be attached to arbitrary LLM agents without task-specific redesign. Motivated by the fact that decision-relevant information is concentrated as abstract knowledge rather than raw experience, we draw on cognitive science to structure episodic memories into a compact, extensible knowledge-centric memory graph that explicitly represents propositional and prescriptive knowledge. This representation enables efficient memory retrieval and reasoning over task-relevant knowledge, rather than verbose raw trajectories, and departs from other graph-based methods like GraphRAG by treating knowledge as the unit of memory access and organization instead of entities or text chunks. We evaluate PlugMem unchanged across three heterogeneous benchmarks (long-horizon conversational question answering, multi-hop knowledge retrieval, and web agent tasks). The results show that PlugMem consistently outperforms task-agnostic baselines and exceeds task-specific memory designs, while also achieving the highest information density under a unified information-theoretic analysis. Code and data are available at https://github.com/TIMAN-group/PlugMem.
format Preprint
id arxiv_https___arxiv_org_abs_2603_03296
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
Yang, Ke
Chen, Zixi
He, Xuan
Jiang, Jize
Galley, Michel
Wang, Chenglong
Gao, Jianfeng
Han, Jiawei
Zhai, ChengXiang
Computation and Language
Artificial Intelligence
Information Retrieval
Long-term memory is essential for large language model (LLM) agents operating in complex environments, yet existing memory designs are either task-specific and non-transferable, or task-agnostic but less effective due to low task-relevance and context explosion from raw memory retrieval. We propose PlugMem, a task-agnostic plugin memory module that can be attached to arbitrary LLM agents without task-specific redesign. Motivated by the fact that decision-relevant information is concentrated as abstract knowledge rather than raw experience, we draw on cognitive science to structure episodic memories into a compact, extensible knowledge-centric memory graph that explicitly represents propositional and prescriptive knowledge. This representation enables efficient memory retrieval and reasoning over task-relevant knowledge, rather than verbose raw trajectories, and departs from other graph-based methods like GraphRAG by treating knowledge as the unit of memory access and organization instead of entities or text chunks. We evaluate PlugMem unchanged across three heterogeneous benchmarks (long-horizon conversational question answering, multi-hop knowledge retrieval, and web agent tasks). The results show that PlugMem consistently outperforms task-agnostic baselines and exceeds task-specific memory designs, while also achieving the highest information density under a unified information-theoretic analysis. Code and data are available at https://github.com/TIMAN-group/PlugMem.
title PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2603.03296