SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning
Proceedings of the VLDB Endowment · 2025-08 · 18 (12) · 4874-4886
DOI: 10.14778/3750601.3750611 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 16.09.2025. Verfasst von Edward Y. Chang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 52 Literaturangaben.
Abstract (Originalsprache)
This paper introduces SagaLLM, a structured multi-agent architecture designed to address four foundational limitations of current LLM-based planning systems: unreliable self-validation, context loss, lack of transactional safeguards, and insufficient inter-agent coordination. While recent frameworks leverage LLMs for task decomposition and multi-agent communication, they often fail to ensure consistency, rollback, or constraint satisfaction across distributed workflows. SagaLLM bridges this gap by integrating the Saga transactional pattern with persistent memory, automated compensation, and independent validation agents. It leverages LLMs' generative reasoning to automate key tasks traditionally requiring hand-coded coordination logic, including state tracking, dependency analysis, log schema generation, and recovery orchestration. Although SagaLLM relaxes strict ACID guarantees, it ensures workflow-wide consistency and recovery through modular checkpointing and compensable execution. Empirical evaluations across planning domains demonstrate that standalone LLMs frequently violate interdependent constraints or fail to recover from disruptions. In contrast, SagaLLM achieves significant improvements in consistency, validation accuracy, and adaptive coordination under uncertainty—establishing a robust foundation for real-world, scalable LLM-based multi-agent systems.
Zitieren
APA
Chang, E. Y., & Geng, L. (2025). SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning. Proceedings of the VLDB Endowment, 18(12), 4874-4886. https://doi.org/10.14778/3750601.3750611
Vancouver
Chang EY, Geng L. SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning. Proceedings of the VLDB Endowment. 2025;18(12):4874-4886. doi:10.14778/3750601.3750611
BibTeX
@article{Chang2025,
author = {Chang, Edward Y. and Geng, Longling},
title = {SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning},
journal = {Proceedings of the VLDB Endowment},
year = {2025},
volume = {18},
number = {12},
pages = {4874--4886},
doi = {10.14778/3750601.3750611}
}
EUVIMED