中文
相关论文

相关论文: Contractual Skills: A GovernSpec Design Framework …

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

Skills are a promising way to improve LLM agent capabilities without retraining, while keeping the added procedure reusable and controllable. However, high-quality skills are still largely written by hand. We introduce SkillGen, a…

The ability of Large Language Models (LLMs) to use external tools unlocks powerful real-world interactions, making rigorous evaluation essential. However, current benchmarks primarily report final accuracy, revealing what models can do but…

计算与语言 · 计算机科学 2026-01-29 Qihao Wang , Yue Hu , Mingzhe Lu , Jiayue Wu , Yanbing Liu , Yuanmin Tang

The quality of training data impacts the performance of pre-trained large language models (LMs). Given a fixed budget of tokens, we study how to best select data that leads to good downstream model performance across tasks. We develop a new…

计算与语言 · 计算机科学 2023-08-01 Mayee F. Chen , Nicholas Roberts , Kush Bhatia , Jue Wang , Ce Zhang , Frederic Sala , Christopher Ré

We introduce SmartEval, a benchmark for systematically evaluating the quality of Solidity smart contracts generated by large language models (LLMs) from natural language specifications. SmartEval provides a corpus of 9,000 generated…

多智能体系统 · 计算机科学 2026-05-12 Abhinav Goel , Agostino Capponi , Alfio Gliozzo , Chaitya Shah

Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and selection are typically governed by external teachers, hand-designed rules, or auxiliary…

人工智能 · 计算机科学 2026-05-13 Min Yang , Jinghua Piao , Xu Xia , Xiaochong Lan , Jiaju Chen , Yongshun Gong , Yong Li

Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pass rate alone. This is insufficient: a skill can improve…

LLM agents increasingly rely on reusable skills (e.g., `SKILL.md`) to execute complex tasks, yet these artifacts lack portability: agent frameworks are highly sensitive to prompt formatting, leading to a large performance variation for the…

密码学与安全 · 计算机科学 2026-05-12 Yipeng Ouyang , Yi Xiao , Yuhao Gu , Xianwei Zhang

The rapid deployment of AI agents in commercial settings has outpaced the development of evaluation methodologies that reflect production realities. Existing benchmarks measure agent capabilities through retrospectively curated tasks with…

Training reliable tool-augmented agents remains a significant challenge, largely due to the difficulty of credit assignment in multi-step reasoning. While process-level reward models offer a promising direction, existing LLM-based judges…

人工智能 · 计算机科学 2026-04-28 Yuxuan Jiang , Francis Ferraro

Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single agentic capability, failing to capture…

In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods still face key challenges, including strategy collapse under…

人工智能 · 计算机科学 2026-05-15 Mingda Zhang , Tiesunlong Shen , Haoran Luo , Wenjin Liu , Zikai Xiao , Erik Cambria , Xiaoying Tang

Agentic AI systems - systems that can pursue goals through multi-step planning and tool-mediated action with limited direct supervision - are moving from experimental prototypes to enterprise deployments. This transition introduces tensions…

计算机与社会 · 计算机科学 2026-05-21 Nelly Dux , Cristina Alaimo , Philippe Roussiere , Abhishek Kumar Mishra

Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are…

人工智能 · 计算机科学 2026-04-10 Ziyu Ma , Shidong Yang , Yuxiang Ji , Xucong Wang , Yong Wang , Yiming Hu , Tongwen Huang , Xiangxiang Chu

Enterprise AI deploys dozens of autonomous agent nodes across workflows, each acting on the same entities with no shared memory and no common governance. We identify five structural challenges arising from this memory governance gap: memory…

人工智能 · 计算机科学 2026-03-19 Hamed Taheri

The Model Context Protocol (MCP) standardizes how AI agents discover and invoke external tools, with over 10,000 active servers and 97 million monthly SDK downloads as of early 2026. Yet MCP does not yet standardize how agents safely…

软件工程 · 计算机科学 2026-04-16 Vasundra Srinivasan

As AI-enabled software systems become more prevalent in smart manufacturing, their role shifts from a reactive to a proactive one that provides context-specific support to machine operators. In the context of an international research…

软件工程 · 计算机科学 2022-06-01 Philipp Haindl , Thomas Hoch , Javier Dominguez , Julen Aperribai , Nazim Kemal Ure , Mehmet Tunçel

Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable procedural knowledge in structured files. However, whether downloaded from third parties or self-generated, these skills are often…

人工智能 · 计算机科学 2026-05-28 Hanyu Wang , Yifan Lan , Bochuan Cao , Lu Lin , Jinghui Chen

As autonomous coding agents become capable of handling increasingly long-horizon tasks, they have gradually demonstrated the potential to complete end-to-end software development. Although existing benchmarks have recently evolved from…

Language agents increasingly improve by reusing \emph{skills} -- structured procedural artifacts distilled from past experience. In particular, \emph{domain-level} and \emph{model-generated} skills are especially promising. They offer fast…