English
Related papers

Related papers: Feedback-based Automated Verification in Vibe Codi…

200 papers

Code language models (CLMs) play a central role in software engineering across both generation and classification tasks. However, these models still exhibit notable mispredictions in real-world applications, even when trained on up-to-date…

Software Engineering · Computer Science 2026-05-20 Ravishka Rathnasuriya , Wei Yang

Chart understanding presents a critical test to the reasoning capabilities of Vision-Language Models (VLMs). Prior approaches face critical limitations: some rely on external tools, making them brittle and constrained by a predefined…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Bohao Tang , Yan Ma , Fei Zhang , Jiadi Su , Ethan Chern , Zhulin Hu , Zhixin Wang , Pengfei Liu , Ya Zhang

Generative AI offers new opportunities for individualized and adaptive learning, e.g., through large language model (LLM)-based feedback systems. While LLMs can produce effective feedback for relatively straightforward conceptual tasks,…

Physics Education · Physics 2026-04-08 Holger Maus , Paul Tschisgale , Fabian Kieser , Stefan Petersen , Peter Wulff

We present a case study of using generative user interfaces, or ``vibe coding,'' a method leveraging large language models (LLMs) for generating code via natural language prompts, to support rapid prototyping in user-centered design (UCD).…

Human-Computer Interaction · Computer Science 2025-07-29 Tianyi Li , Tanay Maheshwari , Alex Voelker

There is a pressing need for better development methods and tools to keep up with the growing demand and increasing complexity of new software systems. New types of user interfaces, the need for intelligent components, sustainability…

Software Engineering · Computer Science 2025-08-01 Jordi Cabot

Automated Code Review (ACR) systems integrating Large Language Models (LLMs) are increasingly adopted in software development workflows, ranging from interactive assistants to autonomous agents in CI/CD pipelines. In this paper, we study…

Software Engineering · Computer Science 2026-04-24 Dimitris Mitropoulos , Nikolaos Alexopoulos , Georgios Alexopoulos , Diomidis Spinellis

Large Language Models (LLMs) have become valuable assistants for developers in code-related tasks. While LLMs excel at traditional programming tasks such as code generation and bug fixing, they struggle with visually-oriented coding tasks,…

Computation and Language · Computer Science 2025-10-28 Bang Xiao , Lingjie Jiang , Shaohan Huang , Tengchao Lv , Yupan Huang , Xun Wu , Lei Cui , Furu Wei

Precisely controlling the length of generated text is a common requirement in real-world applications. However, despite significant advancements in following human instructions, Large Language Models (LLMs) still struggle with this task. In…

Computation and Language · Computer Science 2026-01-08 Meiman Xiao , Ante Wang , Qingguo Hu , Zhongjian Miao , Huangjun Shen , Longyue Wang , Weihua Luo , Jinsong Su

A fundamental limitation of Text-to-Code is that no guarantee can be obtained about the correctness of the generated code. Therefore, to ensure its correctness, the generated code still has to be reviewed, tested, and maintained by…

Software Engineering · Computer Science 2026-05-15 Haoze Wu , Rocky Klopfenstein , Keith Farkas , Nina Narodytska

Large Language Models (LLMs) have made tremendous strides in code generation, but existing research fails to account for the dynamic nature of software development, marked by frequent library updates. This gap significantly limits LLMs'…

Software Engineering · Computer Science 2024-10-17 Tongtong Wu , Weigang Wu , Xingyu Wang , Kang Xu , Suyu Ma , Bo Jiang , Ping Yang , Zhenchang Xing , Yuan-Fang Li , Gholamreza Haffari

Recently, Large Language Models (LLMs) have showcased their potential in various natural language processing tasks, including code generation. However, while significant progress has been made in adapting LLMs to generate code for several…

Machine Learning · Computer Science 2024-07-29 Erica Coppolillo , Francesco Calimeri , Giuseppe Manco , Simona Perri , Francesco Ricca

The notable success of large language models (LLMs) has sparked an upsurge in building language agents to complete various complex tasks. We present AMOR, an agent framework based on open-source LLMs, which reasons with external knowledge…

Computation and Language · Computer Science 2024-10-28 Jian Guan , Wei Wu , Zujie Wen , Peng Xu , Hongning Wang , Minlie Huang

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…

Software Engineering · Computer Science 2026-01-06 Logan Murphy , Aren A. Babikian , Marsha Chechik

Recent advances in Large language models (LLMs) have demonstrated their promising capabilities of generating robot operation code to enable LLM-driven robots. To enhance the reliability of operation code generated by LLMs, corrective…

Robotics · Computer Science 2026-02-25 Wenhao Wang , Yi Rong , Yanyan Li , Long Jiao , Jiawei Yuan

CodeLLMs have demonstrated remarkable advancements in software engineering tasks. However, while these models can generate functionally correct code, they often produce code that is inefficient in terms of runtime. This inefficiency is…

Software Engineering · Computer Science 2024-12-24 Chengran Yang , Hong Jin Kang , Jieke Shi , David Lo

Code reviews are a critical yet time-consuming aspect of modern software development, increasingly challenged by growing system complexity and the demand for faster delivery. This paper presents a study conducted at WirelessCar Sweden AB,…

Generative AI is reshaping product design practices through "vibe coding," where product team members express intent in natural language and AI translates it into functional prototypes and code. Despite rapid adoption, little research has…

Human-Computer Interaction · Computer Science 2026-05-04 Jie Li , Youyang Hou , Laura Lin , Ruihao Zhu , Hancheng Cao , Abdallah El Ali

Reinforcement Learning from AI Feedback (RLAIF) has demonstrated significant potential across various domains, including mitigating harm in LLM outputs, enhancing text summarization, and mathematical reasoning. This paper introduces an…

Computation and Language · Computer Science 2024-07-01 Sujan Dutta , Sayantan Mahinder , Raviteja Anantha , Bortik Bandyopadhyay

Planning is a crucial task for agents in task oriented dialogs (TODs). Human agents typically resolve user issues by following predefined workflows, decomposing workflow steps into actionable items, and performing actions by executing APIs…

Computation and Language · Computer Science 2024-06-06 Shamik Roy , Sailik Sengupta , Daniele Bonadiman , Saab Mansour , Arshit Gupta

Large Language Models (LLMs) have significantly transformed the educational landscape, offering new tools for students, instructors, and teaching assistants. This paper investigates the application of LLMs in assisting teaching assistants…

Human-Computer Interaction · Computer Science 2024-07-25 Anishka IIITD , Diksha Sethi , Nipun Gupta , Shikhar Sharma , Srishti Jain , Ujjwal Singhal , Dhruv Kumar