Context-Value-Action Architecture for Value-Driven Large Language Model Agents

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, TianZe, Sun, Sirui, Xie, Yuhang, Zhang, Xin, Wu, Zhiqiang, Song, Guojie
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913011780812800
author Zhang, TianZe
Sun, Sirui
Xie, Yuhang
Zhang, Xin
Wu, Zhiqiang
Song, Guojie
author_facet Zhang, TianZe
Sun, Sirui
Xie, Yuhang
Zhang, Xin
Wu, Zhiqiang
Song, Guojie
contents Large Language Models (LLMs) have shown promise in simulating human behavior, yet existing agents often exhibit behavioral rigidity, a flaw frequently masked by the self-referential bias of current "LLM-as-a-judge" evaluations. By evaluating against empirical ground truth, we reveal a counter-intuitive phenomenon: increasing the intensity of prompt-driven reasoning does not enhance fidelity but rather exacerbates value polarization, collapsing population diversity. To address this, we propose the Context-Value-Action (CVA) architecture, grounded in the Stimulus-Organism-Response (S-O-R) model and Schwartz's Theory of Basic Human Values. Unlike methods relying on self-verification, CVA decouples action generation from cognitive reasoning via a novel Value Verifier trained on authentic human data to explicitly model dynamic value activation. Experiments on CVABench, which comprises over 1.1 million real-world interaction traces, demonstrate that CVA significantly outperforms baselines. Our approach effectively mitigates polarization while offering superior behavioral fidelity and interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05939
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Context-Value-Action Architecture for Value-Driven Large Language Model Agents
Zhang, TianZe
Sun, Sirui
Xie, Yuhang
Zhang, Xin
Wu, Zhiqiang
Song, Guojie
Artificial Intelligence
Human-Computer Interaction
Large Language Models (LLMs) have shown promise in simulating human behavior, yet existing agents often exhibit behavioral rigidity, a flaw frequently masked by the self-referential bias of current "LLM-as-a-judge" evaluations. By evaluating against empirical ground truth, we reveal a counter-intuitive phenomenon: increasing the intensity of prompt-driven reasoning does not enhance fidelity but rather exacerbates value polarization, collapsing population diversity. To address this, we propose the Context-Value-Action (CVA) architecture, grounded in the Stimulus-Organism-Response (S-O-R) model and Schwartz's Theory of Basic Human Values. Unlike methods relying on self-verification, CVA decouples action generation from cognitive reasoning via a novel Value Verifier trained on authentic human data to explicitly model dynamic value activation. Experiments on CVABench, which comprises over 1.1 million real-world interaction traces, demonstrate that CVA significantly outperforms baselines. Our approach effectively mitigates polarization while offering superior behavioral fidelity and interpretability.
title Context-Value-Action Architecture for Value-Driven Large Language Model Agents
topic Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2604.05939