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

2026-02-23

AI Summary

This work addresses the prevalent issue of stylistic homogenization in literary translation by large language models, which often obscures an author’s distinctive voice. Framing style fidelity as a signal processing problem, the study introduces the Style Feature Spectrum (SFS)—a novel representation based on wavelet packet transform that quantifies literary style as a computable spectral signal. Leveraging this representation, the authors propose a dynamic multi-agent collaboration framework in which specialized translation agents are orchestrated according to the SFS to form adaptive, customized workflows. This approach overcomes the limitations of static architectures, achieving semantic accuracy on par with strong baselines across multiple literary translation benchmarks while demonstrating statistically significant improvements in style preservation.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Adversarial Agents

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• literary translation
• style fidelity
• large language models
• stylistic variation
• multi-agent system

Innovation

• Stylistic Feature Spectrum
• wavelet packet transform
• multi-agent system
• style fidelity
• literary translation