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

Source: [Context-Value-Action Architecture for Value-Driven Large Language Model Agents](<https://www.sota2.com/research/paper/69d5e13e7d0172140ec75c9f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-11T06:00:01.545Z

Authors: TianZe Zhang, Sirui Sun, Yuhang Xie, Xin Zhang, Zhiqiang Wu, Guojie Song

Published: 2026-04-07T14:34:20.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Human Behavior Modeling on CVABench (test)](<https://www.sota2.com/research/sota/human-behavior-modeling-on-cvabench-test.md>): Human Behavior Modeling; CVABench (test); Media Linguistic TTR: 0.04.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.05939>)

[PDF](<https://arxiv.org/pdf/2604.05939.pdf>)
