Memory Management and Contextual Consistency for Long-Running Low-Code Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Xu, Jiexi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912615433764864
author Xu, Jiexi
author_facet Xu, Jiexi
contents The rise of AI-native Low-Code/No-Code (LCNC) platforms enables autonomous agents capable of executing complex, long-duration business processes. However, a fundamental challenge remains: memory management. As agents operate over extended periods, they face "memory inflation" and "contextual degradation" issues, leading to inconsistent behavior, error accumulation, and increased computational cost. This paper proposes a novel hybrid memory system designed specifically for LCNC agents. Inspired by cognitive science, our architecture combines episodic and semantic memory components with a proactive "Intelligent Decay" mechanism. This mechanism intelligently prunes or consolidates memories based on a composite score factoring in recency, relevance, and user-specified utility. A key innovation is a user-centric visualization interface, aligned with the LCNC paradigm, which allows non-technical users to manage the agent's memory directly, for instance, by visually tagging which facts should be retained or forgotten. Through simulated long-running task experiments, we demonstrate that our system significantly outperforms traditional approaches like sliding windows and basic RAG, yielding superior task completion rates, contextual consistency, and long-term token cost efficiency. Our findings establish a new framework for building reliable, transparent AI agents capable of effective long-term learning and adaptation.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25250
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Memory Management and Contextual Consistency for Long-Running Low-Code Agents
Xu, Jiexi
Artificial Intelligence
Software Engineering
I.2.1; H.3.3; D.2.2
The rise of AI-native Low-Code/No-Code (LCNC) platforms enables autonomous agents capable of executing complex, long-duration business processes. However, a fundamental challenge remains: memory management. As agents operate over extended periods, they face "memory inflation" and "contextual degradation" issues, leading to inconsistent behavior, error accumulation, and increased computational cost. This paper proposes a novel hybrid memory system designed specifically for LCNC agents. Inspired by cognitive science, our architecture combines episodic and semantic memory components with a proactive "Intelligent Decay" mechanism. This mechanism intelligently prunes or consolidates memories based on a composite score factoring in recency, relevance, and user-specified utility. A key innovation is a user-centric visualization interface, aligned with the LCNC paradigm, which allows non-technical users to manage the agent's memory directly, for instance, by visually tagging which facts should be retained or forgotten. Through simulated long-running task experiments, we demonstrate that our system significantly outperforms traditional approaches like sliding windows and basic RAG, yielding superior task completion rates, contextual consistency, and long-term token cost efficiency. Our findings establish a new framework for building reliable, transparent AI agents capable of effective long-term learning and adaptation.
title Memory Management and Contextual Consistency for Long-Running Low-Code Agents
topic Artificial Intelligence
Software Engineering
I.2.1; H.3.3; D.2.2
url https://arxiv.org/abs/2509.25250