Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.19840 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908848686628864 |
|---|---|
| author | Wu, Jingzhuo Zhang, Jiajun Jin, Keyan Ma, Dehua Wang, Junbo |
| author_facet | Wu, Jingzhuo Zhang, Jiajun Jin, Keyan Ma, Dehua Wang, Junbo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19840 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SAMAS: A Spectrum-Guided Multi-Agent System for Achieving Style Fidelity in Literary Translation Wu, Jingzhuo Zhang, Jiajun Jin, Keyan Ma, Dehua Wang, Junbo Computation and Language 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. |
| title | SAMAS: A Spectrum-Guided Multi-Agent System for Achieving Style Fidelity in Literary Translation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.19840 |