Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yuen, Sizhe, Medina, Francisco Gomez, Su, Ting, Du, Yali, Sobey, Adam J.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.08997
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915721778298880
author Yuen, Sizhe
Medina, Francisco Gomez
Su, Ting
Du, Yali
Sobey, Adam J.
author_facet Yuen, Sizhe
Medina, Francisco Gomez
Su, Ting
Du, Yali
Sobey, Adam J.
contents Multi-agent systems built on Large Language Models (LLMs) show exceptional promise for complex collaborative problem-solving, yet they face fundamental challenges stemming from context window limitations that impair memory consistency, role adherence, and procedural integrity. This paper introduces Intrinsic Memory Agents, a novel framework that addresses these limitations through agent-specific memories that evolve intrinsically with agent outputs. Specifically, our method maintains role-aligned memory that preserves specialized perspectives while focusing on task-relevant information. Our approach utilises a generic memory template applicable to new problems without the need to hand-craft specific memory prompts. We benchmark our approach on the PDDL, FEVER, and ALFWorld datasets, comparing its performance to existing state-of-the-art multi-agentic memory approaches and showing state-of-the-art or comparable performance across all three, with the highest consistency. An additional evaluation is performed on a complex data pipeline design task, and we demonstrate that our approach produces higher quality designs across 5 metrics: scalability, reliability, usability, cost-effectiveness, and documentation, plus additional qualitative evidence of the improvements. Our findings suggest that addressing memory limitations through intrinsic approaches can improve the capabilities of multi-agent LLM systems on structured planning tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2508_08997
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
Yuen, Sizhe
Medina, Francisco Gomez
Su, Ting
Du, Yali
Sobey, Adam J.
Artificial Intelligence
Multi-agent systems built on Large Language Models (LLMs) show exceptional promise for complex collaborative problem-solving, yet they face fundamental challenges stemming from context window limitations that impair memory consistency, role adherence, and procedural integrity. This paper introduces Intrinsic Memory Agents, a novel framework that addresses these limitations through agent-specific memories that evolve intrinsically with agent outputs. Specifically, our method maintains role-aligned memory that preserves specialized perspectives while focusing on task-relevant information. Our approach utilises a generic memory template applicable to new problems without the need to hand-craft specific memory prompts. We benchmark our approach on the PDDL, FEVER, and ALFWorld datasets, comparing its performance to existing state-of-the-art multi-agentic memory approaches and showing state-of-the-art or comparable performance across all three, with the highest consistency. An additional evaluation is performed on a complex data pipeline design task, and we demonstrate that our approach produces higher quality designs across 5 metrics: scalability, reliability, usability, cost-effectiveness, and documentation, plus additional qualitative evidence of the improvements. Our findings suggest that addressing memory limitations through intrinsic approaches can improve the capabilities of multi-agent LLM systems on structured planning tasks.
title Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
topic Artificial Intelligence
url https://arxiv.org/abs/2508.08997