Integrating External Tools with Large Language Models to Improve Accuracy
Nripesh Niketan, Hadj Batatia
备注：
9 pages, 3 figures, 2 tables. Extended version of paper published in Proceedings of International Conference on Information Technology and Applications, Springer Nature Singapore, 2025, pp. 409-421. This version includes additional experimental results comparing against GPT-4o, LLaMA-Large, Mistral-Large, and Phi-Large, expanded evaluation methodology, and enhanced analysis
发表信息：
Proceedings of International Conference on Information Technology and Applications, Springer Nature Singapore, 2025, pp. 409-421
本文探讨如何改进大语言模型（LLMs）的查询。众所周知，若缺乏相关上下文信息，LLMs可能提供低质量回复或倾向于产生幻觉。多项倡议已提出将LLMs与外部工具集成，为其提供最新数据以提升准确性。本文提出一个框架，通过集成外部工具来增强LLMs在教育场景下回答查询的能力。具体而言，我们开发了一个允许访问外部API以请求额外相关信息的框架。集成的工具还可提供计算能力，如计算器或日历。所提框架使用来自Multi-Modal Language Understanding（MMLU）集合的数据集进行了评估。该数据由数学和科学推理问题组成。与最先进语言模型相比的结果表明，所提方法显著提升了性能。我们的Athena框架在数学推理中达到83%的准确率，在科学推理中达到88%，大幅优于所有测试模型，包括GPT-4o、LLaMA-Large、Mistral-Large、Phi-Large和GPT-3.5，其中最佳基线模型（LLaMA-Large）仅分别达到67%和79%。这些有前景的结果为围绕LLMs创建复杂计算生态系统铺平了道路，使其使用更自然，以支持各类任务与活动。
英文摘要：
This paper deals with improving querying large language models (LLMs). It is well-known that without relevant contextual information, LLMs can provide poor quality responses or tend to hallucinate. Several initiatives have proposed integrating LLMs with external tools to provide them with up-to-date data to improve accuracy. In this paper, we propose a framework to integrate external tools to enhance the capabilities of LLMs in answering queries in educational settings. Precisely, we develop a framework that allows accessing external APIs to request additional relevant information. Integrated tools can also provide computational capabilities such as calculators or calendars. The proposed framework has been evaluated using datasets from the Multi-Modal Language Understanding (MMLU) collection. The data consists of questions on mathematical and scientific reasoning. Results compared to state-of-the-art language models show that the proposed approach significantly improves performance. Our Athena framework achieves 83% accuracy in mathematical reasoning and 88% in scientific reasoning, substantially outperforming all tested models including GPT-4o, LLaMA-Large, Mistral-Large, Phi-Large, and GPT-3.5, with the best baseline model (LLaMA-Large) achieving only 67% and 79% respectively. These promising results open the way to creating complex computing ecosystems around LLMs to make their use more natural to support various tasks and activities.
Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees
National Key Laboratory for Novel Software Technology（计算机软件新技术国家重点实验室）；School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）；Alibaba International Digital Commerce（阿里巴巴国际数字商业集团）；Pazhou Laboratory (Huangpu)（琶洲实验室（黄埔））
When Tools Hurt LLM Reasoning: State-Dependent Belief Revision under External Evidence
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Monash University（莫纳什大学）；Tencent Hunyuan（腾讯混元）
ShizishanGPT: An Agricultural Large Language Model Integrating Tools and Resources
College of Informatics, Huazhong Agricultural University（华中农业大学信息学院）；Industrial AI Research Centre, University of South Australia（南澳大学工业人工智能中心）；College of Plant Science and Technology, Huazhong Agricultural University（华中农业大学植物科学技术学院）
FAITH: Factuality Alignment through Integrating Trustworthiness and Honestness
Tsinghua University, Institute for Interdisciplinary Information Sciences（清华大学，交叉信息研究院）；Shanghai Qi Zhi Institute（上海期智研究院）；South China Normal University, School of Electronic Science and Engineering（华南师范大学，电子科学与工程学院）；Guangzhou Richstone Data Technologies Co., Ltd.（广州瑞驰数据技术有限公司）；LMU Munich & Munich Center for Machine Learning（慕尼黑大学 & 慕尼黑机器学习中心）
Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary
University of Edinburgh（爱丁堡大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Northwestern University（西北大学）；Princeton University（普林斯顿大学）；The Chinese University of Hong Kong（香港中文大学）
Empowering Multimodal LLMs with External Tools: A Comprehensive Survey
School of Automation Science and Engineering, Xi’an Jiaotong University（自动化科学与工程学院，西安交通大学）；Interdisciplinary Graduate Programme, Nanyang Technological University（跨学科研究生项目，南洋理工大学）；Lenovo Research, Lenovo（联想研究院，联想）；School of Computer Science and Technology, Xi’an Jiaotong University（计算机科学与技术学院，西安交通大学）；College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）
EcoAct: Economic Agent Determines When to Register What Action
Pennsylvania State University（宾夕法尼亚州立大学）；Microsoft（微软公司）；The University of Washington（华盛顿大学）；University of British Columbia（不列颠哥伦比亚大学）；Google DeepMind（谷歌DeepMind）
Integrating remote sensing data assimilation, deep learning and large language model for interactive wheat breeding yield prediction
College of Biosystems Engineering and Food Science, Zhejiang University（浙江大学生物系统工程与食品科学学院）；College of Agriculture and Biotechnology, Zhejiang University（浙江大学农业与生物技术学院）；The University of Manchester（曼彻斯特大学）；University of Toronto（多伦多大学）
针对小麦育种产量预测精度与工具易用性不足，提出融合遥感数据同化、时序深度学习模型及 RAG 增强 LLM 的交互式 Web 预测工具。
Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generation
Department of Computer and Data Sciences, Case Western Reserve University（计算机与数据科学系，凯斯西储大学）；Department of Design and Innovation, Case Western Reserve University（设计与创新系，凯斯西储大学）
OralAgent: Integrating Reasoning, Tools, and Knowledge for Interactive Dental Image Analysis
Faculty of Dentistry, the University of Hongkong, Hong Kong SAR, China（香港大学牙科学院，中国香港特别行政区）；Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA（匹兹堡大学电气与计算机工程系，美国宾夕法尼亚州匹兹堡）；Shenzhen University, China（深圳大学，中国）；Department of Craniomaxillofacial Surgery, Shanghai Ninth People’s Hospital, China（上海第九人民医院口腔颌面外科部，中国）；Nanyang technological University, Singapore（南洋理工大学，新加坡）；School of Biomedical Engineering, Southern Medical University, China（南方医科大学生物医学工程学院，中国）；Singapore University of Technology and Design, Singapore（新加坡科技设计大学，新加坡）；University of Auckland, new zealand（奥克兰大学，新西兰）；Shanghai Artificial Intelligence Laboratory , China（上海人工智能实验室，中国）
