中文
相关论文

相关论文: Intent Formalization: A Grand Challenge for Reliab…

200 篇论文

Autoformalization addresses the scarcity of data for Automated Theorem Proving (ATP) by translating mathematical problems from natural language into formal statements. Efforts in recent work shift from directly prompting large language…

Code readability is fundamental to software quality and maintainability. Poor readability extends development time, increases bug-inducing risks, and contributes to technical debt. With the rapid advancement of Large Language Models, AI…

软件工程 · 计算机科学 2026-03-17 Kyogo Horikawa , Kosei Horikawa , Yutaro Kashiwa , Hidetake Uwano , Hajimu Iida

A rigorous formalization of desired system requirements is indispensable when performing any verification task. This often limits the application of verification techniques, as writing formal specifications is an error-prone and…

计算机科学中的逻辑 · 计算机科学 2023-03-10 Matthias Cosler , Christopher Hahn , Daniel Mendoza , Frederik Schmitt , Caroline Trippel

The growing adoption of large language models in legal practice brings both significant promise and serious risk. Legal professionals stand to benefit from AI that can reason over contracts, draft documents, and analyze sources at scale,…

人工智能 · 计算机科学 2026-05-15 Olivia Peiyu Wang , Leilani H. Gilpin

Terminal-agent benchmarks have become a primary signal for measuring the coding and system-administration capabilities of large language models. As the market for evaluation environments grows, so does the pressure to ship tasks quickly,…

人工智能 · 计算机科学 2026-05-01 Ivan Bercovich

Large Language Models (LLMs) have emerged as transformative tools for natural language understanding and user intent resolution, enabling tasks such as translation, summarization, and, increasingly, the orchestration of complex workflows.…

软件工程 · 计算机科学 2025-11-12 Justus Flerlage , Alexander Acker , Odej Kao

The quality of software produced by students is often poor. How to teach students to develop good quality software has long been a topic in computer science education and research. We must conclude that we still do not have a good answer to…

软件工程 · 计算机科学 2023-09-06 Arno Broeders , Ruud Hermans , Sylvia Stuurman , Lex Bijlsma , Harrie Passier

In the software industry, artificial intelligence (AI) has been utilized more and more in software development activities. In some activities, such as coding, AI has already been an everyday tool, but in software testing activities AI it…

软件工程 · 计算机科学 2025-04-08 Katja Karhu , Jussi Kasurinen , Kari Smolander

Autoformalization is the process of automatically translating from natural language mathematics to formal specifications and proofs. A successful autoformalization system could advance the fields of formal verification, program synthesis,…

机器学习 · 计算机科学 2022-05-26 Yuhuai Wu , Albert Q. Jiang , Wenda Li , Markus N. Rabe , Charles Staats , Mateja Jamnik , Christian Szegedy

Artificial intelligence systems have achieved remarkable capability in natural language processing, perception and decision-making tasks. However, their behaviour often remains opaque and difficult to verify, limiting their applicability in…

软件工程 · 计算机科学 2026-04-15 Arshad Beg , Diarmuid O'Donoghue , Rosemary Monahan

Large language models (LLMs) are increasingly used to generate requirements specifications, design documents, code, and test cases. In contrast, much less attention has been given to a more difficult assurance problem: statically verifying…

软件工程 · 计算机科学 2026-05-19 Zhi Quan Zhou , Dave Towey , Tsong Yueh Chen

Data analysis is challenging as it requires synthesizing domain knowledge, statistical expertise, and programming skills. Assistants powered by large language models (LLMs), such as ChatGPT, can assist analysts by translating natural…

人机交互 · 计算机科学 2024-03-05 Ken Gu , Ruoxi Shang , Tim Althoff , Chenglong Wang , Steven M. Drucker

When software artifacts are generated by AI models ("vibe coding"), human engineers assume responsibility for validating them. Ideally, this validation would be done through the creation of a formal proof of correctness. However, this is…

软件工程 · 计算机科学 2026-01-06 Logan Murphy , Aren A. Babikian , Marsha Chechik

Autoformalization, the task of automatically translating natural language descriptions into a formal language, poses a significant challenge across various domains, especially in mathematics. Recent advancements in large language models…

计算与语言 · 计算机科学 2024-12-09 Zenan Li , Yifan Wu , Zhaoyu Li , Xinming Wei , Xian Zhang , Fan Yang , Xiaoxing Ma

AI agentic programming is an emerging paradigm where large language model (LLM)-based coding agents autonomously plan, execute, and interact with tools such as compilers, debuggers, and version control systems. Unlike conventional code…

软件工程 · 计算机科学 2025-09-16 Huanting Wang , Jingzhi Gong , Huawei Zhang , Jie Xu , Zheng Wang

Historically, programming language semantics has focused on assigning a precise mathematical meaning to programs. That meaning is a function from the program's input domain to its output domain determined solely by its syntactic structure.…

Intent-Based Networking (IBN) aims to simplify operating heterogeneous infrastructures by translating high-level intents into enforceable policies and assuring compliance. However, dependable automation remains difficult because (i)…

网络与互联网体系结构 · 计算机科学 2026-03-26 Md. Kamrul Hossain , Walid Aljoby

This position paper argues that securing LLM agents requires first defining an end-to-end correctness property that specifies when an agent's execution faithfully reflects the user's intent. Modern LLM agents operate over an…

密码学与安全 · 计算机科学 2026-05-19 Wenjie Qu , Ming Xu , Peiran Wang , Shengfang Zhai , Jiaheng Zhang , Dawn Song

Requirements are informal and semi-formal descriptions of the expected behavior of a system. They are usually expressed in the form of natural language sentences and checked for errors manually, e.g., by peer reviews. Manual checks are…

计算机科学中的逻辑 · 计算机科学 2018-04-30 Simone Vuotto

Large Language Models based on transformer algorithms have revolutionized Artificial Intelligence by enabling verbal interaction with machines akin to human conversation. These AI agents have surpassed the Turing Test, achieving confusion…