Tool calling enables large language models (LLMs) to interact with external environments through tool invocation, providing a practical way to overcome the limitations of pretraining. However, the effectiveness of tool use depends heavily on the quality of the associated documentation and knowledge base context. These materials are usually written for human users and are often misaligned with how LLMs interpret information. This problem is even more pronounced in industrial settings, where hundreds of tools with overlapping functionality create challenges in scalability, variability, and ambiguity. We propose Verification-Guided Context Optimization (VGCO), a framework that uses LLMs as editors to automatically refine tool-related documentation and knowledge base context. VGCO works in two stages. First, Evaluation collects real-world failure cases and identifies mismatches between tools and their context. Second, Optimization performs hierarchical editing through offline learning with structure-aware, in-context optimization. The novelty of our LLM editors has three main aspects. First, they use a hierarchical structure that naturally integrates into the tool-calling workflow. Second, they are state-aware, action-specific, and verification-guided, which constrains the search space and enables efficient, targeted improvements. Third, they enable cost-efficient sub-task specialization, either by prompt engineering large editor models or by post-training smaller editor models. Unlike prior work that emphasizes multi-turn reasoning, VGCO focuses on the single-turn, large-scale tool-calling problem and achieves significant improvements in accuracy, robustness, and generalization across LLMs.
ToolACE: Winning the Points of LLM Function Calling
Shanghai Jiao Tong University（上海交通大学）；University of Science and Technology of China（中国科学技术大学）；Huawei Noah’s Ark Lab（华为诺亚实验室）；Huawei Technologies Co., Ltd（华为技术有限公司）；Tsinghua University（清华大学）；The Chinese University of Hong Kong（香港中文大学）
本文提出自动智能体数据合成流水线 ToolACE，通过自演化 API 构建、多智能体对话生成和双层验证，训练出可匹敌 GPT-4 的 8B 函数调用模型。
Transparency as Architecture: Structural Compliance Gaps in EU AI Act Article 50 II
Technichal University Berlin XpaliNLP Group（柏林工业大学 XpaliNLP 组）；Research Center for Artificial Intelligence (DFKI)（人工智能研究中心（DFKI））；Center for European Research on Trusted AI (CERTAIN)（欧洲可信人工智能研究中心（CERTAIN））
MedScope: Incentivizing "Think with Videos" for Clinical Reasoning via Coarse-to-Fine Tool Calling
College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China（上海交通大学医学院健康科学与技术学院）；Fudan University, Shanghai, China（复旦大学）；Shanghai Innovation Institute, Shanghai, China（上海创新研究院）；Tsinghua University, Beijing, China（清华大学）；Shanghai Artificial Intelligence Laboratory, Shanghai, China（上海人工智能实验室）；The Chinese University of Hong Kong, Hong Kong, China（香港中文大学）；Ruijin Hospital, Shanghai Jiaotong University, Shanghai, China（上海交通大学瑞金医院）
The steep learning curve of formal technologies is a well-known barrier to the adoption of formal verification tools in industry. This paper presents VSCode-PVS, a modern integrated development environment for the Prototype Verification System (PVS). This new environment integrates the editing and proof management functionalities of PVS in Visual Studio Code, a popular code editor widely used by software developers. VSCode-PVS provides functionalities that developers expect to find in modern verification tools, but are not available in the standard Emacs front-end of PVS, such as auto-completi…
Are Large Language Models Capable of Deep Relational Reasoning? Insights from DeepSeek-R1 and Benchmark Comparisons
School of Professional Education and Executive Development（专业教育与执行发展学院）；The Hong Kong Polytechnic University（香港理工大学）；School of Mathematics and Statistics（数学与统计学学院）；Beijing Institute of Technology（北京理工大学）；Department of Mathematics（数学系）；The University of Hong Kong（香港大学）
