arXiv AI
Translating the Translator: Decomposing the Cost of English-Forced Inter-Agent Communication
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Sep 22
BabelArena: A Large-Scale Multilingual Benchmark for LLM Agents
arXiv:2609.23490v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly execute multi-step workflows through tool use and interaction with users and environments. However, curr...
arXiv AI
Oct 21
LoWAgent: A Low-Resource Multilingual Benchmark for Web Agents
arXiv:2610.27205v1 Announce Type: cross Abstract: Web agents are typically evaluated on English-language interfaces, leaving their ability to operate across the world's multilingual websites largely...
Hugging Face Trending Papers
Aug 9
OmnilingualGAIA2: Evaluating the Multilingual Gap in Frontier AI Agents
Agentic benchmarks aim to measure how well AI agents plan, search, execute, and recover within realistic multi-tool environments, but they are almost exclusively in English. As AI agents are globally deployed to a linguistically diverse user base, whether agentic competence measured in English transfers to other languages remains an open question.
arXiv AI
Jun 3
Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing
arXiv:2606. 03618v1 Announce Type: new Abstract: AI-assisted coding agents are bottlenecked by input-token cost.
arXiv AI
Sep 1
Terminal-Bench-LILT: Multilingual Agentic Coding Benchmark Grounded in Language, Region, and Culture
arXiv:2608.28641v1 Announce Type: cross Abstract: Most evaluations for coding agents are conducted exclusively in English, which does not reflect real-world multilingual deployment. We present Termin...
arXiv AI
Jul 3
Multilingual Prompt Localization for Agent-as-a-Judge: Language and Backbone Sensitivity in Requirement-Level Evaluation
arXiv:2604. 04532v2 Announce Type: replace-cross Abstract: Evaluation language is typically treated as a fixed English default in agentic code benchmarks, yet we show that changing the judge's language can invert backbone rankings.