@InProceedings{yang-EtAl:2026:wmt1,
  author    = {Yang, Mengpeng  and  Xia, Tian  and  Yang, Jingxu  and  Chen, Chao  and  Sun, Yabo  and  Liu, Qiang},
  title     = {TRIVE: A Tri-Fusion Verified Translation Agent},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {1470--1483},
  abstract  = {For the WMT26 General Machine Translation Task (Unconstrained Track), we propose TRIVE (Tri-Fusion Verified Translation Agent), a model-agnostic multi-agent translation framework. TRIVE organizes translation as a closed loop of Generation--Fusion--Verification--Correction: it first generates candidates in parallel under three complementary strategies---Faithful, Fluent, and Free---then synthesizes a draft that balances semantic fidelity and natural expression, and finally iteratively refines the output via rule-based validation and large language model evaluation. Because each module is implemented primarily via prompting, TRIVE can be directly overlaid onto diverse backbone models without task-specific fine-tuning. Experiments show that overlaying TRIVE on multiple backbones consistently improves instruction-following translation quality. Finally, we submitted Gemini-3.5-Flash + TRIVE as our primary system to WMT26.},
  url       = {https://aclanthology.org/2026.wmt-1.84}
}