The Context-Value-Action architecture decouples reasoning from action in LLM agents via a human-data-trained Value Verifier, mitigating polarization and outperforming prompt-based methods on a large real-world benchmark.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLM framework converts facial action unit sequences to text, fuses with responses, and regresses to personality scores, reporting lower errors and higher correlations than baselines on AVI-6.
citing papers explorer
-
Context-Value-Action Architecture for Value-Driven Large Language Model Agents
The Context-Value-Action architecture decouples reasoning from action in LLM agents via a human-data-trained Value Verifier, mitigating polarization and outperforming prompt-based methods on a large real-world benchmark.
-
LLM-based Multimodal Personality Recognition via Facial Action Unit-Text Semantic Fusion
LLM framework converts facial action unit sequences to text, fuses with responses, and regresses to personality scores, reporting lower errors and higher correlations than baselines on AVI-6.