中文
相关论文

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

200 篇论文

Verification-aware programming languages such as Dafny and F* provide means to formally specify and prove properties of a program. Although the problem of checking an implementation against a specification can be defined mechanically, there…

编程语言 · 计算机科学 2024-10-17 Shuvendu K. Lahiri

With the advent of AI-based coding engines, it is possible to convert natural language requirements to executable code in standard programming languages. However, AI-generated code can be unreliable, and the natural language requirements…

软件工程 · 计算机科学 2024-11-06 Martin Mirchev , Andreea Costea , Abhishek Kr Singh , Abhik Roychoudhury

Large language models (LLMs) have shown great potential in automating significant aspects of coding by producing natural code from informal natural language (NL) intent. However, when interacting with LLMs, users have no guarantees that the…

Formal software specification is known to enable early error detection and explicit invariants, yet it has seen limited industrial adoption due to its high notation overhead and the expertise required to use traditional formal languages.…

软件工程 · 计算机科学 2026-01-16 Antonio Abu Nassar , Eitan Farchi

Software correctness is ensured mathematically through formal verification, which involves the resources of generating formal requirement specifications and having an implementation that must be verified. Tools such as model-checkers and…

软件工程 · 计算机科学 2025-08-29 Arshad Beg , Diarmuid O'Donoghue , Rosemary Monahan

AI agents have recently shown significant promise in software engineering. Much public attention has been transfixed on the topic of code generation from Large Language Models (LLMs) via a prompt. However, software engineering is much more…

软件工程 · 计算机科学 2025-09-23 Abhik Roychoudhury

Early-stage specifications of safety-critical systems are typically expressed in natural language, making it difficult to derive formal properties suitable for verification and needed to guarantee safety. While recent Large Language Model…

软件工程 · 计算机科学 2026-04-21 Alberto Tagliaferro , Bruno Guindani , Livia Lestingi , Matteo Rossi

Formal specifications, such as pre- and post-conditions provide a solid basis for performing thorough program verification. However, developers rarely provide such formal specifications, hence if AI could help in constructing them, it would…

软件工程 · 计算机科学 2026-03-19 I. S. W. B. Prasetya , Fitsum Kifetew , Davide Prandi

One of the most challenging tasks in software specifications engineering for a multi-agent system is to ensure correctness. As these systems have high concurrency, often have dynamic environments, the formal specification and verification…

软件工程 · 计算机科学 2015-01-22 Nadeem Akhtar

Recent advancements on Large Language Models (LLMs) enable AI Agents to automatically generate and execute multi-step plans to solve complex tasks. However, since LLM's content generation process is hardly controllable, current LLM-based…

机器学习 · 计算机科学 2024-08-13 Zelong Li , Wenyue Hua , Hao Wang , He Zhu , Yongfeng Zhang

Interactive proof assistants are computer programs carefully constructed to check a human-designed proof of a mathematical claim with high confidence in the implementation. However, this only validates truth of a formal claim, which may…

编程语言 · 计算机科学 2023-10-09 Colin S. Gordon , Sergey Matskevich

Recent advances in large language models have enabled developers to generate software by conversing with artificial intelligence systems rather than writing code directly. This paper introduces vibe coding, an emerging AI-native programming…

软件工程 · 计算机科学 2025-10-22 Vinay Bamil

Modern AI agents optimize programs by refactoring source code to trigger trusted compiler transformations. This preserves program semantics and reduces source code pollution, making the program easier to maintain and portable across…

编程语言 · 计算机科学 2026-04-16 Akash Deo , Simone Campanoni , Tommy McMichen

Improper parsing of attacker-controlled input is a leading source of software security vulnerabilities, especially when programmers transcribe informal format descriptions in RFCs into efficient parsing logic in low-level, memory unsafe…

软件工程 · 计算机科学 2024-05-08 Sarah Fakhoury , Markus Kuppe , Shuvendu K. Lahiri , Tahina Ramananandro , Nikhil Swamy

Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit…

人工智能 · 计算机科学 2026-02-25 Ved Sirdeshmukh , Marc Wetter

Autoformalization, the process of translating informal statements into formal logic, has gained renewed interest with the emergence of powerful Large Language Models (LLMs). While LLMs show promise in generating structured outputs from…

计算与语言 · 计算机科学 2025-11-18 Mihir Gupte , Ramesh S

With the rapid advancement of AI, software engineering increasingly relies on AI-driven approaches, particularly language models (LMs), to enhance code performance. However, the trustworthiness and reliability of LMs remain significant…

软件工程 · 计算机科学 2025-03-19 Jingzhi Gong

LLM agents are increasingly deployed to automate real-world tasks by invoking APIs through natural language instructions. While powerful, they often suffer from misinterpretation of user intent, leading to the agent's actions that diverge…

软件工程 · 计算机科学 2025-10-27 Shiwei Feng , Xiangzhe Xu , Xuan Chen , Kaiyuan Zhang , Syed Yusuf Ahmed , Zian Su , Mingwei Zheng , Xiangyu Zhang

Generative artificial intelligence (GenAI) and agentic systems are moving software engineering from code-centric production toward intent-centric human-agent work in which natural language, repository context, tools, tests, and governance…

软件工程 · 计算机科学 2026-05-13 Elyson De La Cruz

AI-assisted code generation tools have revolutionized software development, offering unprecedented efficiency and scalability. However, multiple studies have consistently highlighted challenges such as security vulnerabilities, reliability…

软件工程 · 计算机科学 2025-06-16 Ahilan Ayyachamy Nadar Ponnusamy
‹ 上一页 1 2 3 10 下一页 ›