SAMAS: A Spectrum-Guided Multi-Agent System for Achieving Style Fidelity in Literary Translation

TL;DR

SAMAS is a novel multi-agent framework that uses a spectrum-based control signal to dynamically preserve literary style in translations, outperforming traditional models in style fidelity.

Contribution

Introduces SAMAS, a spectrum-guided multi-agent system that dynamically adapts translation workflows to better preserve literary style.

Findings

Achieves competitive semantic accuracy with improved style fidelity.

Uses wavelet packet transform to quantify literary style as a control signal.

Demonstrates statistically significant advantage in style preservation.

Abstract

Modern large language models (LLMs) excel at generating fluent and faithful translations. However, they struggle to preserve an author's unique literary style, often producing semantically correct but generic outputs. This limitation stems from the inability of current single-model and static multi-agent systems to perceive and adapt to stylistic variations. To address this, we introduce the Style-Adaptive Multi-Agent System (SAMAS), a novel framework that treats style preservation as a signal processing task. Specifically, our method quantifies literary style into a Stylistic Feature Spectrum (SFS) using the wavelet packet transform. This SFS serves as a control signal to dynamically assemble a tailored workflow of specialized translation agents based on the source text's structural patterns. Extensive experiments on translation benchmarks show that SAMAS achieves competitive semantic accuracy against strong baselines, primarily by leveraging its statistically significant advantage in style fidelity.