@InProceedings{shao-EtAl:2026:wmt,
  author    = {Shao, Liangying  and  Wu, Xinwei  and  Huang, Yichong  and  Wang, Jifang  and  Xu, Ruoxi  and  Shi, Ling  and  Yang, Baosong  and  Xu, Linlong},
  title     = {Wayfinder: An Agentic Ensemble-and-Postcheck System for WMT26 GenMT},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {1412--1420},
  abstract  = {This paper presents Wayfinder, our submission system for the WMT26 General Machine Translation (GenMT) shared task. GenMT evaluates document-level translation under natural-language instructions, where structural preservation, formatting constraints, and output cleanliness are part of translation quality. Rather than training a new translation model, Wayfinder treats four API-based system outputs as a document-level candidate pool and produces one final hypothesis through a four-stage agentic pipeline. It aggregates source, instruction, metadata, candidates, and a DeepSeek-V4-Pro ranking-then-scoring signal; applies an anonymized pick-or-rewrite agent; and runs a conservative postcheck for severe objective defects. During development, a judge-guided loop compares outputs with a GPT-5.5 baseline, analyzes loss cases, updates prompts and repair constraints, and selectively reprocesses difficult documents. In automatic pairwise evaluation against GPT-5.5, Wayfinder obtains a pooled document-level weighted win rate of 0.6537 and remains above parity in every evaluated direction. The results suggest that candidate-pool translation, constrained agentic selection, conservative repair, and selective judge-guided iteration are practical components for instruction-conditioned shared-task MT.},
  url       = {https://aclanthology.org/2026.wmt-1.78}
}