Large Language Model (LLM) agents have demonstrated strong performance in long-horizon tasks, particularly in planning, tool usage, and interaction with external environments. However, most existing benchmarks implicitly assume a monolingual setting, where the entire execution process, including reasoning, tool invocation, and output generation, is conducted in a single language. In contrast, real-world applications often involve multilingual inputs and outputs within a unified workflow, yet the interaction between multilinguality and agentic execution remains underexplored.
In this work, we introduce PolyWorkBench, a benchmark for evaluating LLM agents on multilingual long-horizon workplace workflows. PolyWorkBench consists of 67 tasks across five domains, including commerce, knowledge work, legal analysis, localization, and manufacturing, where agents must process heterogeneous multilingual inputs, perform iterative reasoning, invoke external tools, and produce structured outputs. To enable comprehensive evaluation, we propose a hybrid framework that combines structural grading, executable verification, and LLM-based semantic assessment. This design allows us to capture both functional correctness and linguistic consistency across complex workflows.
Empirical results show that state-of-the-art LLM agents suffer significant performance degradation in multilingual workflow settings compared to their monolingual counterparts. Our analysis suggests that multilinguality introduces compounding effects across reasoning and execution steps, highlighting the importance of jointly modeling language variation and procedural decision-making in agent evaluation.
Blogger's Review: The introduction of PolyWorkBench addresses the gap in evaluating LLM agents in multilingual environments, emphasizing the complexity of multilingual processing in real-world applications. This benchmark not only enhances the comprehensiveness of evaluations but also offers new directions for future research, making it a noteworthy development in the field.