融合工具与多模型推理，提升双语数学题求解准确率
Tool-Augmented Hybrid Ensemble Reasoning with Distillation for Bilingual Mathematical Problem Solving
- 用多个大模型协同，通过自适应路由选择最佳推理路径
- 在数学题上达到91.2%准确率，延迟降低37%且结果更稳定
- 适合需要高精度计算的跨语言教育应用或智能助手
双语数学问题求解需在语言推理与符号计算间建立清晰联系。大型语言模型虽擅长语言理解，但在精确计算方面表现较弱。本文提出HERALD（Hybrid Ensemble Reasoning with Adaptive Learning and Distillation）框架，结合NuminaMath-7B-TIR、GPT-4o和Mistral-7B，利用自适应路由、基于工具的强化学习与知识蒸馏，连接不同推理路径。置信度校准确保权重稳定，双路径验证保障结果正确性。强化学习控制工具调用以减少冗余，知识蒸馏在不损失准确率的前提下降低延迟37%。实验表明，结合符号验证、自适应集成与双语微调，可实现流畅推理与精准计算的统一。HERALD为多语言数学推理提供了高效、稳定且清晰的解决方案。
原文摘要 · Abstract (English)
Bilingual mathematical problem solving needs a clear link between language reasoning and symbolic calculation. Large language models often handle language well but are weak in accurate computation. This paper presents HERALD (Hybrid Ensemble Reasoning with Adaptive Learning and Distillation), a framework that joins reasoning and calculation using NuminaMath-7B-TIR, GPT-4o, and Mistral-7B. HERALD uses adaptive routing, tool-based reinforcement learning, and knowledge distillation to connect different reasoning paths. Confidence calibration keeps weighting stable, and dual-path checking keeps results correct. Reinforcement learning controls tool use to cut redundancy, and distillation lowers delay without hurting accuracy. The system shows that combining symbolic checking, adaptive ensembles, and bilingual fine-tuning helps achieve both fluent reasoning and precise calculation. HERALD offers a practical solution for multilingual mathematical reasoning with better accuracy, stability, and clarity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。