中文
相关论文

相关论文: Skills as Verifiable Artifacts: A Trust Schema and…

200 篇论文

The companion paper introduced a four-level verification lattice on agent-skill manifests (unverified, declared, tested, formal) and left the top level aspirational. This paper closes that gap. We give a precise semantics for skill…

人工智能 · 计算机科学 2026-05-26 Alfredo Metere

Modern Large Language Model (LLM) systems are assembled from third-party artifacts such as pre-trained weights, fine-tuning adapters, datasets, dependency packages, and container images, fetched through automated pipelines. This speed comes…

密码学与安全 · 计算机科学 2026-04-01 Zhuoran Tan , Jeremy Singer , Christos Anagnostopoulos

Large language model (LLM) ecosystems such as Claude Code and ChatGPT increasingly rely on skills: packages of natural-language instructions and executable tools. Once in the LLM's context, skill content cannot be reliably separated from…

密码学与安全 · 计算机科学 2026-05-08 Tingda Shen , Yebo Feng , Konglin Zhu , Xiaojun Jia , Yang Liu , Lin Zhang

Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration into reusable workflows. This makes skills useful, but it also…

密码学与安全 · 计算机科学 2026-05-15 Haomin Zhuang , Hanwen Xing , Yujun Zhou , Yuchen Ma , Yue Huang , Yili Shen , Yufei Han , Xiangliang Zhang

LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this…

密码学与安全 · 计算机科学 2026-02-26 David Schmotz , Luca Beurer-Kellner , Sahar Abdelnabi , Maksym Andriushchenko

Large language model (LLM) agents increasingly rely on reusable skills: capability packages that combine instructions, control flow, constraints, and tool calls. In current agent systems, however, skills are still represented by text-heavy…

计算与语言 · 计算机科学 2026-05-05 Qiliang Liang , Hansi Wang , Zhong Liang , Yang Liu

The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute…

密码学与安全 · 计算机科学 2026-01-16 Yi Liu , Weizhe Wang , Ruitao Feng , Yao Zhang , Guangquan Xu , Gelei Deng , Yuekang Li , Leo Zhang

Current AI-assisted engineering workflows lack a built-in mechanism to maintain task-level verification and regulatory traceability at machine-speed delivery. Agile V addresses this gap by embedding independent verification and audit…

软件工程 · 计算机科学 2026-02-25 Christopher Koch , Joshua Andreas Wellbrock

Verification and validation of agentic behavior have been suggested as important research priorities in efforts to reduce risks associated with the creation of general artificial intelligence (Russell et al 2015). In this paper we question…

人工智能 · 计算机科学 2016-10-12 David J. Jilk

Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by an average of 16.2~percentage points across diverse domains. Yet the same benchmarks…

人工智能 · 计算机科学 2026-05-26 Samuel Jacob Chacko , James Hugglestone , Chashi Mahiul Islam , Xiuwen Liu

Large language model (LLM)-based agents that reason, plan, and act through tools, memory, and structured interaction are emerging as a promising paradigm for automating complex workflows. Recent systems such as OpenClaw and Claude Code…

信息检索 · 计算机科学 2026-05-27 Yingli Zhou , Wang Shu , Yaodong Su , Wenchuan Du , Yixiang Fang , Xuemin Lin

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…

人工智能 · 计算机科学 2026-05-07 Chenglin Yang

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

Skills, i.e., structured workflow instructions distilled for large language models (LLMs), are becoming an increasingly important mechanism for improving agent performance on real-world downstream tasks. However, as the open-source skill…

计算与语言 · 计算机科学 2026-05-29 Jiahao Ying , Boxian Ai , Wei Tang , Siyuan Liu , Yixin Cao

Enabling continual learning in LLMs remains a key unresolved research challenge. In a recent announcement, a frontier LLM company made a step towards this by introducing Agent Skills, a framework that equips agents with new knowledge based…

机器学习 · 计算机科学 2025-10-31 David Schmotz , Sahar Abdelnabi , Maksym Andriushchenko

Increasing a ML model accuracy is not enough, we must also increase its trustworthiness. This is an important step for building resilient AI systems for safety-critical applications such as automotive, finance, and healthcare. For that…

人工智能 · 计算机科学 2022-05-03 Gusseppe Bravo-Rocca , Peini Liu , Jordi Guitart , Ajay Dholakia , David Ellison , Miroslav Hodak

Agent Skills is an emerging open standard that defines a modular, filesystem-based packaging format enabling LLM-based agents to acquire domain-specific expertise on demand. Despite rapid adoption across multiple agentic platforms and the…

密码学与安全 · 计算机科学 2026-04-06 Zhiyuan Li , Jingzheng Wu , Xiang Ling , Xing Cui , Tianyue Luo

Agentic systems increasingly rely on reusable procedural capabilities, \textit{a.k.a., agentic skills}, to execute long-horizon workflows reliably. These capabilities are callable modules that package procedural knowledge with explicit…

密码学与安全 · 计算机科学 2026-02-25 Yanna Jiang , Delong Li , Haiyu Deng , Baihe Ma , Xu Wang , Qin Wang , Guangsheng Yu

We consider the setting of stochastic multiagent systems modelled as stochastic multiplayer games and formulate an automated verification framework for quantifying and reasoning about agents' trust. To capture human trust, we work with a…

计算机科学中的逻辑 · 计算机科学 2019-05-17 Xiaowei Huang , Marta Kwiatkowska , Maciej Olejnik

LLM agents operating in open environments face escalating risks from indirect prompt injection, particularly within the tool stream where manipulated metadata and runtime feedback hijack execution flow. Existing defenses encounter a…

密码学与安全 · 计算机科学 2026-01-15 Junda Lin , Zhaomeng Zhou , Zhi Zheng , Shuochen Liu , Tong Xu , Yong Chen , Enhong Chen
‹ 上一页 1 2 3 10 下一页 ›