Text2Mem: A Unified Memory Operation Language for Memory Operating System

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yi, Yang, Lihai, Chen, Boyu, Zou, Gongyi, Xu, Kerun, Tang, Bo, Xiong, Feiyu, Chen, Siheng, Li, Zhiyu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914109218357248
author Wang, Yi
Yang, Lihai
Chen, Boyu
Zou, Gongyi
Xu, Kerun
Tang, Bo
Xiong, Feiyu
Chen, Siheng
Li, Zhiyu
author_facet Wang, Yi
Yang, Lihai
Chen, Boyu
Zou, Gongyi
Xu, Kerun
Tang, Bo
Xiong, Feiyu
Chen, Siheng
Li, Zhiyu
contents Large language model agents increasingly depend on memory to sustain long horizon interaction, but existing frameworks remain limited. Most expose only a few basic primitives such as encode, retrieve, and delete, while higher order operations like merge, promote, demote, split, lock, and expire are missing or inconsistently supported. Moreover, there is no formal and executable specification for memory commands, leaving scope and lifecycle rules implicit and causing unpredictable behavior across systems. We introduce Text2Mem, a unified memory operation language that provides a standardized pathway from natural language to reliable execution. Text2Mem defines a compact yet expressive operation set aligned with encoding, storage, and retrieval. Each instruction is represented as a JSON based schema instance with required fields and semantic invariants, which a parser transforms into typed operation objects with normalized parameters. A validator ensures correctness before execution, while adapters map typed objects either to a SQL prototype backend or to real memory frameworks. Model based services such as embeddings or summarization are integrated when required. All results are returned through a unified execution contract. This design ensures safety, determinism, and portability across heterogeneous backends. We also outline Text2Mem Bench, a planned benchmark that separates schema generation from backend execution to enable systematic evaluation. Together, these components establish the first standardized foundation for memory control in agents.
format Preprint
id arxiv_https___arxiv_org_abs_2509_11145
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Text2Mem: A Unified Memory Operation Language for Memory Operating System
Wang, Yi
Yang, Lihai
Chen, Boyu
Zou, Gongyi
Xu, Kerun
Tang, Bo
Xiong, Feiyu
Chen, Siheng
Li, Zhiyu
Computation and Language
Programming Languages
Large language model agents increasingly depend on memory to sustain long horizon interaction, but existing frameworks remain limited. Most expose only a few basic primitives such as encode, retrieve, and delete, while higher order operations like merge, promote, demote, split, lock, and expire are missing or inconsistently supported. Moreover, there is no formal and executable specification for memory commands, leaving scope and lifecycle rules implicit and causing unpredictable behavior across systems. We introduce Text2Mem, a unified memory operation language that provides a standardized pathway from natural language to reliable execution. Text2Mem defines a compact yet expressive operation set aligned with encoding, storage, and retrieval. Each instruction is represented as a JSON based schema instance with required fields and semantic invariants, which a parser transforms into typed operation objects with normalized parameters. A validator ensures correctness before execution, while adapters map typed objects either to a SQL prototype backend or to real memory frameworks. Model based services such as embeddings or summarization are integrated when required. All results are returned through a unified execution contract. This design ensures safety, determinism, and portability across heterogeneous backends. We also outline Text2Mem Bench, a planned benchmark that separates schema generation from backend execution to enable systematic evaluation. Together, these components establish the first standardized foundation for memory control in agents.
title Text2Mem: A Unified Memory Operation Language for Memory Operating System
topic Computation and Language
Programming Languages
url https://arxiv.org/abs/2509.11145