翻译译者：分解英语强制智能体间通信的成本
Translating the Translator: Decomposing the Cost of English-Forced Inter-Agent Communication
浏览论文内容
中文总结 AI 辅助
本研究评估多智能体LLM架构中英语强制通信的代价，发现其显著降低非英语任务性能，提出母语路由可减少翻译损失。
中文摘要 AI 辅助
多智能体大语言模型架构（如LangChain和AutoGen）在很大程度上假设英语作为智能体间内部通信的通用语言，即使最终用户的任务是非英语的。我们通过评估一个双智能体提取-回答核心，并在英语强制条件下增加一个回译智能体，使用Aya-23-8B模型在四种类型多样的语言（印地语、中文、西班牙语、阿拉伯语；每种语言n=300）上填补了这一空白。我们比较了母语流水线与英语强制流水线（后者包含从英语到用户语言的最终回译步骤）。我们发现了一个统计显著的英语强制税（通过了严格的Bonferroni校正），该税将英语路由的成本与一般多智能体编排开销分离开来。与母语多智能体执行相比，强制通过英语进行智能体间通信使精确匹配准确率降低了13.0个百分点（西班牙语）至30.6个百分点（印地语）。使用chrF分数作为英语参考词汇重叠的诊断指标，我们发现较低的重叠与流水线失败密切相关，这与翻译损失是观察到的性能下降的重要贡献者一致。这些发现表明，当源语言和目标语言在类型上相距较远时，在智能体框架中采用母语路由具有令人信服的理由，从而减少复合的翻译税。
英文摘要
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.
发表机构
- Åbo Akademi University（奥博学术大学）
- Anglia Ruskin University（安格利亚鲁斯金大学）
机构由 AI 辅助整理，请以论文原文为准。
