Metraipolis › archive › dc_02e9b78298f9
Translating the Translator: Decomposing the Cost of English-Forced Inter-Agent Communication — arXiv:2609.15079
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.15079
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T22:41:34.654Z
- SHA-256 of the archived text
15db23b1c3a4e4cbc186c2cb2f3822d9e3ef4a26320be611c44102b61c7919c8- Stable URL of this page
https://metraipolis.com/documento/dc_02e9b78298f9
How to cite
Translating the Translator: Decomposing the Cost of English-Forced Inter-Agent Communication — arXiv:2609.15079 — arXiv (en), https://arxiv.org/abs/2609.15079 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_02e9b78298f9 (Metraipolis archive dc_02e9b78298f9, sha256 15db23b1c3a4e4cbc186c2cb2f3822d9e3ef4a26320be611c44102b61c7919c8)
BibTeX
@misc{dc02e9b78298f9,
title = {Translating the Translator: Decomposing the Cost of English-Forced Inter-Agent Communication — arXiv:2609.15079},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.15079},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_02e9b78298f9; sha256 15db23b1c3a4e4cbc186c2cb2f3822d9e3ef4a26320be611c44102b61c7919c8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15079. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-agent LLM architectures, such as LangChain and AutoGen, largely assume English as the lingua franca for internal inter-agent communication, even when the end-user task is non-English. We fill this gap by evaluating a two-agent extraction-answer core, with an additional back-translation agent in the English-forced condition, across four typologically diverse languages (Hindi, Chinese, Spanish, Arabic; n = 300 per language) using the Aya-23-8B model. We compare a native-language pipeline to an English-forced one (which incorporates a final back-translation step from English to the user's language). We discover a statistically significant English-Forcing Tax (surviving a strict Bonferroni correction) that isolates the cost of English routing from general multi-agent orchestration overhead. Forcing inter-agent communication through English reduces Exact Match accuracy by 13.0 percentage points (Spanish) up to 30.6 percentage points (Hindi) compared to native-language multi-agent execution. Using chrF scores as a diagnostic measure of English-reference lexical overlap, we find that lower overlap is strongly associated with pipeline failure, consistent with translation loss being an important contributor to the observed performance drop. These findings suggest a compelling case for native-language routing in agent frameworks when the source and target languages are typologically distant, reducing a compounding translation tax. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.MA). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2609.15079 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T22:21:04.243Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).