中文
相关论文

相关论文: Tool Forge: A Validation-Carrying Toolchain for Go…

200 篇论文

This work proposes an agentic, intent-driven end-to-end (E2E) orchestration framework that integrates intent co-creation with a Test-Driven Quality Assurance paradigm. In this framework, autonomous agents iteratively refine a user's initial…

网络与互联网体系结构 · 计算机科学 2026-04-28 Christos Tranoris , Besiana Agko , Kostis Trantzas , Irene Denazi

Nowadays, agentic AI is emerging as a transformative paradigm for next-generation communication networks, promising to evolve large language models (LLMs) from passive chatbots into autonomous operators. However, unleashing this potential…

网络与互联网体系结构 · 计算机科学 2026-01-14 Yinqiu Liu , Ruichen Zhang , Dusit Niyato , Abbas Jamalipour , Trung Q. Duong , Dong In Kim

Large Language Models (LLMs) augmented with external tools have demonstrated remarkable capabilities in complex reasoning tasks. However, existing frameworks rely heavily on natural language reasoning to determine when tools can be invoked…

计算与语言 · 计算机科学 2026-01-09 Yanming Liu , Xinyue Peng , Jiannan Cao , Xinyi Wang , Songhang Deng , Jintao Chen , Jianwei Yin , Xuhong Zhang

Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks by dynamically utilising external software components. However, these tools must be implemented in advance by human developers,…

计算与语言 · 计算机科学 2025-06-02 Georg Wölflein , Dyke Ferber , Daniel Truhn , Ognjen Arandjelović , Jakob Nikolas Kather

Research on self-evolving language agents has accelerated, drawing increasing attention to their ability to create, adapt, and maintain tools from task requirements. However, existing benchmarks predominantly rely on predefined…

软件工程 · 计算机科学 2026-03-09 Bowei Xia , Mengkang Hu , Shijian Wang , Jiarui Jin , Wenxiang Jiao , Yuan Lu , Kexin Li , Ping Luo

Tool-using agents are increasingly expected to operate across realistic professional workflows, where they must interpret multimodal inputs, coordinate external tools, inspect intermediate artifacts, and revise their actions before…

人工智能 · 计算机科学 2026-05-19 Zhiqiang Liu , Wenhui Dong , Yilang Tan , Yuwen Qu , Haochen Yin , Chenyang Si

The emergence of LLMs has catalyzed a paradigm shift in autonomous agent development, enabling systems capable of reasoning, planning, and executing complex multi-step tasks. However, existing agent frameworks often suffer from…

人工智能 · 计算机科学 2026-01-21 Akbar Anbar Jafari , Cagri Ozcinar , Gholamreza Anbarjafari

Agentic AI coding systems can inspect repositories, plan implementation steps, edit files, call tools, run tests, and submit pull requests. These capabilities make software and hardware development faster in some settings, but current…

软件工程 · 计算机科学 2026-05-21 Christopher Koch

IDE-Bench is a comprehensive framework for evaluating AI IDE agents on real-world software engineering tasks through an IDE-native tool interface. We present a Dockerized test harness that goes beyond raw terminal execution, granting models…

软件工程 · 计算机科学 2026-02-02 Spencer Mateega , Jeff Yang , Tiana Costello , Shaurya Jadhav , Nicole Tian , Agustin Garcinuño

As large language models (LLMs) advance, their inability to autonomously execute tasks by directly interacting with external tools remains a critical limitation. Traditional methods rely on inputting tool descriptions as context, which is…

计算与语言 · 计算机科学 2025-04-01 Renxi Wang , Xudong Han , Lei Ji , Shu Wang , Timothy Baldwin , Haonan Li

Tool-calling agents are increasingly deployed in real-world customer-facing workflows. Yet most studies on tool-calling agents focus on idealized settings with general, fixed, and well-specified tasks. In real-world applications, user…

Tool-integrated LLMs can retrieve, compute, and take real-world actions via external tools, but reliability remains a key bottleneck. We argue that failures stem from both tool-use accuracy (how well an agent invokes a tool) and intrinsic…

人工智能 · 计算机科学 2026-04-02 Hy Dang , Quang Dao , Meng Jiang

The analysis of formal models that include quantitative aspects such as timing or probabilistic choices is performed by quantitative verification tools. Broad and mature tool support is available for computing basic properties such as…

Large Language Model (LLM) Agents leverage the advanced reasoning capabilities of LLMs in real-world applications. To interface with an environment, these agents often rely on tools, such as web search or database APIs. As the agent…

人工智能 · 计算机科学 2025-03-12 Ivan Milev , Mislav Balunović , Maximilian Baader , Martin Vechev

As AI agents transition from research prototypes to enterprise production systems, the tool interfaces they consume remain rooted in human-oriented CRUD paradigms. This paper identifies five fundamental architectural mismatches between…

人工智能 · 计算机科学 2026-05-12 Kai Pan

Recent large language models (LLMs) advancements sparked a growing research interest in tool assisted LLMs solving real-world challenges, which calls for comprehensive evaluation of tool-use capabilities. While previous works focused on…

Closed-loop tool-using agents are increasingly evaluated in executable web, code, and micro-task environments, but benchmark reports often conflate workloads, action-generating drivers, and the evidence admitted for systems-facing claims.…

软件工程 · 计算机科学 2026-05-13 Zhiqing Zhong , Zhijing Ye , Jiamin Wang , Xiaodong Yu

Large language models generate plausible code but cannot verify correctness. Existing multi-agent systems simulate execution or leave verification optional. We introduce execution-grounded verification as a first-class principle: every code…

软件工程 · 计算机科学 2026-04-16 Rajesh Kumar , Waqar Ali , Junaid Ahmed , Najma Imtiaz Ali , Shaban Usman

Existing GUI agent models relying on coordinate-based one-step visual grounding struggle with generalizing to varying input resolutions and aspect ratios. Alternatives introduce coordinate-free strategies yet suffer from learning under…

机器学习 · 计算机科学 2026-02-04 Xiaoce Wang , Guibin Zhang , Junzhe Li , Jinzhe Tu , Chun Li , Ming Li

Multi-agent systems powered by large language models (LLMs) are transforming enterprise automation, yet systematic evaluation methodologies for assessing tool-use reliability remain underdeveloped. We introduce a comprehensive diagnostic…

人工智能 · 计算机科学 2026-01-26 Donghao Huang , Gauri Malwe , Zhaoxia Wang
‹ 上一页 1 2 3 10 下一页 ›