Translating the Translator: Decomposing the Cost of English-Forced Inter-Agent Communication

arXiv:2609.15079 · cs.CL, cs.AI, cs.MA · Submitted 2026-09-14 · Read on arXiv

cs.CL, cs.AI, cs.MA

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: Accepted at The 2nd Workshop for Research on Agent Language Models at EMNLP 2026

License: http://creativecommons.org/licenses/by/4.0/

The gist: 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.

Terminology

Accuracy — 22× in this paper · explained in 1 episode
Core — 6× in this paper · explained in 2 episodes
Multi-Agent System — 4× in this paper · explained in 6 episodes
Quantization — 4× in this paper · explained in 12 episodes
F1 Score — 3× in this paper · explained in 3 episodes
Failure Modes — 3× in this paper · explained in 3 episodes
Hallucination — 3× in this paper · explained in 4 episodes
Transformer — 3× in this paper · explained in 2 episodes
Benchmark — 2× in this paper · explained in 2 episodes
Agent Core — 1× in this paper · explained in 2 episodes
Agentic Framework — 1× in this paper · explained in 6 episodes
Cross-lingual Transfer — 1× in this paper · explained in 2 episodes
Edge Deployment — 1× in this paper · explained in 2 episodes
Edge Devices — 1× in this paper · explained in 2 episodes
Embeddings — 1× in this paper · explained in 2 episodes
Fidelity — 1× in this paper · explained in 2 episodes
Generalization — 1× in this paper · explained in 13 episodes
International Conference on Learning Representations — 1× in this paper
Interpretability — 1× in this paper · explained in 15 episodes
Mechanistic interpretability — 1× in this paper · explained in 2 episodes
Pairwise Comparisons — 1× in this paper · explained in 2 episodes
Prompt Engineering — 1× in this paper · explained in 4 episodes
SQuAD Exact Match — 1× in this paper
Semantic Drift — 1× in this paper · explained in 3 episodes
Semantic Similarity — 1× in this paper · explained in 2 episodes
Trace — 1× in this paper · explained in 2 episodes
Transferability — 1× in this paper · explained in 4 episodes

Abstract

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.

Translating the Translator: Decomposing the Cost of English-Forced Inter-Agent Communication

Terminology

Abstract

Sources

Related papers