English(EN)PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages
新的基准和工具提升了LLM的数学推理能力 · 跟踪6个来源
作者PulseAugur 编辑部·[7 个来源]·
研究人员为大型语言模型（LLMs）在数学推理方面引入了新的基准和评估方法。MIRA-Math侧重于最小化信息请求，模型必须请求一个缺失的事实来解决数学问题。此外，PluraMath扩展了现有的多语言基准，以包含代表性不足的语言，突显了高资源和低资源语言环境之间的性能差距。另外，一项评估SageMath增强型LLM代理的研究表明，当这些模型能够访问计算工具时，性能会显著提高，其中Qwen 3.7-Max和GPT-5.5表现出显著的改进。
AI
arXiv:2607.07391v1 Announce Type: new Abstract: Mathematical reasoning benchmarks typically provide all facts needed to solve each problem, while interactive benchmarks often mix reasoning with tools, retrieval, and long-horizon dialogue. We introduce MIRA-Math, a benchmark for a…
arXiv cs.AI
TIER_1English(EN)·Pavel Snopov, German Magai·
arXiv:2607.06820v1 Announce Type: new Abstract: Recent advances in AI for Mathematics have focused largely on autoformalization and theorem proving, leaving the role of Computer Algebra Systems (CAS) in agentic LLM workflows underexplored. We propose a ReAct-style agentic setup t…
Mathematical reasoning benchmarks typically provide all facts needed to solve each problem, while interactive benchmarks often mix reasoning with tools, retrieval, and long-horizon dialogue. We introduce MIRA-Math, a benchmark for a narrower diagnostic capability: solving mathema…
arXiv:2607.05992v1 Announce Type: cross Abstract: Mathematical reasoning has become a central task for evaluating and tuning reasoning Large Language Models (LLMs), yet existing benchmarks remain heavily biased toward high-resource languages, with English and Chinese dominating b…
arXiv:2605.19723v2 Announce Type: replace-cross Abstract: Mathematical reasoning is essential for problem-solving in education, science, and industry, serving as a crucial benchmark for evaluating artificial intelligence systems. As Large Language Models (LLMs) improve their reas…
Mathematical reasoning has become a central task for evaluating and tuning reasoning Large Language Models (LLMs), yet existing benchmarks remain heavily biased toward high-resource languages, with English and Chinese dominating both pre-training corpora and evaluation suites. Th…
PluraMath extends the PolyMath dataset to 18 underrepresented languages, revealing persistent gaps in multilingual mathematical reasoning performance between high-resource and low-resource languages.
