Multi-Agent Debate for Machine Translation: A Case Study on English-Japanese Translation

Zhan Shen, Jason Naradowsky, Xiaotian Wang, Yusuke Miyao


Abstract
As machine translation increasingly requires deeper contextual, linguistic, and cultural understanding, multi-agent collaboration has emerged as a promising approach. Multi-agent debate (MAD) frameworks, in which multiple agents deliberate to produce a final output, have shown strong performance on objective tasks, but remain underexplored in translation, where multiple valid renderings often exist. We adapt three MAD frameworks for English-Japanese translation and evaluate them against strong generative baselines, reasoning-capable LLMs, and a prompt-based self-reflection baseline. Across general-domain and culturally grounded datasets, the Society of Mind (SoM) variant yields the strongest results in the English-to-Japanese direction, showing that zero-shot translations leave substantial room for improvement through structured deliberation. Yet the gains of debate are front-loaded: later rounds do not reliably improve quality and often reintroduce translation errors. Diagnostic and error-span analyses show that hand-designed debate protocols tend to over-revise already strong translations, leading to semantic drift and process-induced degradation. These findings highlight both the promise and the limitations of agentic translation, and suggest that effective debate-based systems require mechanisms for preserving strong intermediate outputs.
Anthology ID:
2026.eamt-1.16
Volume:
Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1)
Month:
June
Year:
2026
Address:
Tilburg, The Netherlands
Editors:
Dimitar Shterionov, Eva Vanmassenhove, Mirella De Sisto, Fred Blain, Javad Pourmostafa Roshan Sharami, Lisa Lepp, Chiara Manna, Argentina Anna Rescigno, Alina Karakanta, Ayla Rigouts Terryn, Manuel Lardelli, Natalia Resende, Elena Murgolo, Janiça Hackenbuchner, Anna Zaretskaya, Miquel Esplà-Gomis, Thierry Etchegoyhen, Dagmar Gromann, Rachel Bawden, Barry Haddow, Sara Szoc, Mikel Forcada, Helena Moniz
Venue:
EAMT
SIG:
Publisher:
European Association for Machine Translation
Note:
Pages:
205–230
Language:
URL:
https://aclanthology.org/2026.eamt-1.16/
DOI:
Bibkey:
Cite (ACL):
Zhan Shen, Jason Naradowsky, Xiaotian Wang, and Yusuke Miyao. 2026. Multi-Agent Debate for Machine Translation: A Case Study on English-Japanese Translation. In Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1), pages 205–230, Tilburg, The Netherlands. European Association for Machine Translation.
Cite (Informal):
Multi-Agent Debate for Machine Translation: A Case Study on English-Japanese Translation (Shen et al., EAMT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.eamt-1.16.pdf