中文
相关论文

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

200 篇论文

Standard automatic methods for recognizing problematic development commits can be greatly improved via the incremental application of human+artificial expertise. In this approach, called EMBLEM, an AI tool first explore the software…

软件工程 · 计算机科学 2020-04-08 Huy Tu , Zhe Yu , Tim Menzies

Coding agents produce rich trajectories while solving software-engineering tasks. To enable agent self-evolution, these trajectories can be distilled into reusable procedural skills that compactly encode experience to guide future behavior.…

人工智能 · 计算机科学 2026-05-26 Yanzhou Li , Yiran Zhang , Xiaoyu Zhang , Xiaoxia Liu , Yang Liu

An agent skill is a configuration package that equips an LLM-driven agent with a concrete capability, such as reading email, executing shell commands, or signing blockchain transactions. Each skill is a hybrid artifact-a structured half…

密码学与安全 · 计算机科学 2026-05-04 Hongbo Wen , Ying Li , Hanzhi Liu , Chaofan Shou , Yanju Chen , Yuan Tian , Yu Feng

This paper presents a new tool learning dataset Seal-Tools, which contains self-instruct API-like tools. Seal-Tools not only offers a large number of tools, but also includes instances which demonstrate the practical application of tools.…

计算与语言 · 计算机科学 2024-05-15 Mengsong Wu , Tong Zhu , Han Han , Chuanyuan Tan , Xiang Zhang , Wenliang Chen

To help evaluate and understand the latent capabilities of language models, this paper introduces an approach using optimized input embeddings, or 'soft prompts,' as a metric of conditional distance between a model and a target behavior.…

机器学习 · 计算机科学 2025-05-22 Ross Nordby

With the rapid evolution of Large Language Model (LLM) agent ecosystems, centralized skill marketplaces have emerged as pivotal infrastructure for augmenting agent capabilities. However, these marketplaces face unprecedented security…

密码学与安全 · 计算机科学 2026-03-24 Zihan Guo , Zhiyu Chen , Xiaohang Nie , Jianghao Lin , Yuanjian Zhou , Weinan Zhang

Autonomous coding agents can produce strong tabular baselines quickly on Kaggle-style tasks. Practical value depends on end-to-end correctness and reliability under time limits. This paper introduces TML-Bench, a tabular benchmark for data…

机器学习 · 计算机科学 2026-03-09 Mykola Pinchuk

Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear. We…

软件工程 · 计算机科学 2026-03-17 Tingxu Han , Yi Zhang , Wei Song , Chunrong Fang , Zhenyu Chen , Youcheng Sun , Lijie Hu

Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skills are typically improved through prompt engineering or by aligning the task LLM itself,…

AI agents are changing the requirements for document parsing. What matters is semantic correctness: parsed output must preserve the structure and meaning needed for autonomous decisions, including correct table structure, precise chart…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Boyang Zhang , Sebastián G. Acosta , Preston Carlson , Sacha Bron , Pierre-Loïc Doulcet , Daniel B. Ospina , Simon Suo

Agentic AI systems plan, use tools, maintain state, and produce multi-step trajectories with external effects. Those properties create a governance problem that differs materially from single-turn generative AI: important risks emerge dur-…

人工智能 · 计算机科学 2026-04-08 Christopher Koch

Complex Verilog Design Problems (CVDP) challenge hardware LLM agents because solving them requires localizing verifier-relevant RTL, testbenches, include paths, and build dependencies inside large repository snapshots, making precise edits,…

人工智能 · 计算机科学 2026-05-22 Zijian Du , Nathaniel Pinckney

Skill ecosystems for LLM agents have matured rapidly, yet recent benchmarks show that providing agents with more skills does not monotonically improve performance -- focused sets of 2-3 skills outperform comprehensive documentation, and…

计算与语言 · 计算机科学 2026-04-21 Tianle Xia , Lingxiang Hu , Yiding Sun , Ming Xu , Lan Xu , Siying Wang , Wei Xu , Jie Jiang

Among the thriving ecosystem of cloud computing and the proliferation of Large Language Model (LLM)-based code generation tools, there is a lack of benchmarking for code generation in cloud-native applications. In response to this need, we…

分布式、并行与集群计算 · 计算机科学 2024-01-17 Yifei Xu , Yuning Chen , Xumiao Zhang , Xianshang Lin , Pan Hu , Yunfei Ma , Songwu Lu , Wan Du , Zhuoqing Mao , Ennan Zhai , Dennis Cai

Contracts are a common type of legal document that frequent in several day-to-day business workflows. However, there has been very limited NLP research in processing such documents, and even lesser in generating them. These contracts are…

计算与语言 · 计算机科学 2021-11-01 Vinay Aggarwal , Aparna Garimella , Balaji Vasan Srinivasan , Anandhavelu N , Rajiv Jain

The rapid adoption of AI agents across domains has made systematic evaluation crucial for ensuring their usefulness and successful production deployment. Evaluation of AI agents typically involves using a fixed set of benchmarks and…

This paper offers a brief review of cognitive verbs typically used in the literature to describe standard spreadsheet practices. The verbs identified are then categorised in terms of Bloom's Taxonomy of Hierarchical Levels, and then rated…

人机交互 · 计算机科学 2008-07-21 Garry Cleere

As Multimodal Large Language Models (MLLMs) advance, multimodal agents show promise in real-world tasks like web navigation and embodied intelligence. However, due to limitations in a lack of external feedback, these agents struggle with…

计算与语言 · 计算机科学 2025-06-27 Tianyi Men , Zhuoran Jin , Pengfei Cao , Yubo Chen , Kang Liu , Jun Zhao

Reusable skills let LLM agents package task-specific procedures, tool affordances, and execution guidance into modular building blocks. As skill ecosystems grow to tens of thousands of entries, exposing every skill at inference time becomes…

Modern clinical practice relies on evidence-based guidelines implemented as compact scoring systems composed of a small number of interpretable decision rules. While machine-learning models achieve strong performance, many fail to translate…

机器学习 · 计算机科学 2026-05-25 Silas Ruhrberg Estévez , Christopher Chiu , Mihaela van der Schaar