Verification-Gated Persona State Transitions for Memory-Augmented Language Agents
Symmetry · 16.06.2026 · 18 (6) · 1037
DOI: 10.3390/sym18061037 ↗Kurz gefasst
Fachartikel in der Zeitschrift Symmetry, online erschienen am 16.06.2026. Verfasst von Fan Li und 3 weiteren Autor:innen. Die Arbeit nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Memory-augmented language agents are increasingly used for long-horizon personalized interaction, but they still struggle to adapt to user-specific evidence without gradually drifting away from a stable and reliable persona. In this paper, we study how to maintain long-term persona invariance while preserving the utility of memory-based personalization. We propose a verification-aware memory framework that separates fast-changing episodic memory from a slow persona state and treats persona evolution as a controlled state transition rather than an unconstrained memory write. At a high level, retrieved evidence can only induce a bounded tentative persona update, and the update is committed only if an external verifier confirms that the resulting symbolic trace satisfies explicit persona specifications. Across long-term memory, personalized dialogue, persona consistency, and over-personalization benchmarks, our method achieves the best overall performance, improving utility metrics on LongMemEval, LoCoMo, and PersonaMem-v2 while reducing hard violation rate from 6.9 to 3.2 and increasing repair success rate from 67.5 to 74.9 on reliability benchmarks. These results show that explicit verification can make memory-augmented agents both more adaptive and more dependable, offering a practical path toward safer long-term personalization.
Zitieren
APA
Li, F., Li, J., Ma, S., & Liu, Y. (2026). Verification-Gated Persona State Transitions for Memory-Augmented Language Agents. Symmetry, 18(6), 1037. https://doi.org/10.3390/sym18061037
Vancouver
Li F, Li J, Ma S, Liu Y. Verification-Gated Persona State Transitions for Memory-Augmented Language Agents. Symmetry. 2026;18(6):1037. doi:10.3390/sym18061037
BibTeX
@article{Li2026,
author = {Li, Fan and Li, Jia and Ma, Siyuan and Liu, Yang},
title = {Verification-Gated Persona State Transitions for Memory-Augmented Language Agents},
journal = {Symmetry},
year = {2026},
volume = {18},
number = {6},
pages = {1037},
doi = {10.3390/sym18061037}
}
EUVIMED