English
Related papers

Related papers: The Kitchen Loop: User-Spec-Driven Development for…

200 papers

LLMs enable qualitative coding at large scale, but assessing reliability remains challenging where human experts seldom agree. We investigate confidence-diversity calibration as a quality assessment framework for accessible coding tasks…

Machine Learning · Computer Science 2025-08-19 Zhilong Zhao , Yindi Liu

LLM-based coding agents are increasingly used to generate code, tests, and documentation. Still, their outputs can be plausible yet misaligned with developer intent and provide limited evidence for review in evolving projects. This limits…

Software Engineering · Computer Science 2026-04-14 Ragib Shahariar Ayon

We study auto research as a closed empirical loop driven by external measurement. Each submitted trial carries a hypothesis, an executable code edit, an evaluator-owned outcome, and feedback that shapes the next proposal. The output is not…

Multiagent Systems · Computer Science 2026-05-08 Jingjie Ning , Xiaochuan Li , Ji Zeng , Hao Kang , Chenyan Xiong

Modern LLM agents increasingly create their own tools at runtime -- from Python functions to API clients -- yet existing benchmarks evaluate them almost exclusively by downstream task completion. This is analogous to judging a software…

Software Engineering · Computer Science 2026-04-02 Alibek T. Kaliyev , Artem Maryanskyy

Large language models (LLMs) have demonstrated an impressive ability to generate codes on competitive programming tasks. However, with limited sample numbers, LLMs still suffer from poor accuracy. Inspired by the process of human…

Software Engineering · Computer Science 2023-09-12 Kechi Zhang , Zhuo Li , Jia Li , Ge Li , Zhi Jin

Automatic programming has seen increasing popularity due to the emergence of tools like GitHub Copilot which rely on Large Language Models (LLMs). At the same time, automatically generated code faces challenges during deployment due to…

Software Engineering · Computer Science 2024-05-16 Michael R. Lyu , Baishakhi Ray , Abhik Roychoudhury , Shin Hwei Tan , Patanamon Thongtanunam

Linux kernel evolution breaks drivers through API/ABI changes, semantic shifts, and security-hardening updates. We introduce DRIVEBENCH, an executable corpus of kernel$\rightarrow$driver co-evolution cases, and AUTODRIVER, a closed-loop,…

Software Engineering · Computer Science 2025-11-25 Arina Kharlamova , Jiawen Liu , Tianyi Zhang , Xinrui Yang , Humaid Alqasimi , Youcheng Sun , Chun Jason Xue

As LLMs make their way into many aspects of our lives, one place that warrants increased scrutiny with LLM usage is scientific research. Using LLMs for generating or analyzing data for research purposes is gaining popularity. But when such…

Human-Computer Interaction · Computer Science 2024-05-13 Chirag Shah

Existing LLM-based EDA agents are often isolated task-specific systems. This leads to repeated engineering effort and limited reuse of successful design and debugging strategies. We present LEGO, a unified skill-based platform for front-end…

Artificial Intelligence · Computer Science 2026-05-19 Jincheng Lou , Ruohan Xu , Jiecheng Ma , Runzhe Tao , Xinyu Qu , Yibo Lin

This paper introduces the first \emph{self-evolving} logic synthesis framework, which leverages Large Language Model (LLM) agents to autonomously improve the source code of \textsc{ABC}, the widely adopted logic synthesis system. Our…

Hardware Architecture · Computer Science 2026-04-17 Cunxi Yu , Haoxing Ren

Scripting interfaces enable users to automate tasks and customize software workflows, but creating scripts traditionally requires programming expertise and familiarity with specific APIs, posing barriers for many users. While Large Language…

Artificial Intelligence · Computer Science 2026-02-09 Paiheng Xu , Gang Wu , Xiang Chen , Tong Yu , Chang Xiao , Franck Dernoncourt , Tianyi Zhou , Wei Ai , Viswanathan Swaminathan

Software testing has progressed toward intelligent automation, yet current AI-based test generators still suffer from static, single-shot outputs that frequently produce invalid, redundant, or non-executable tests due to the lack of…

Software Engineering · Computer Science 2026-01-07 Saba Naqvi , Mohammad Baqar , Nawaz Ali Mohammad

We propose a novel model- and feature-based approach to development of vehicle software systems, where the end architecture is not explicitly defined. Instead, it emerges from an iterative process of search and optimization given certain…

Software Engineering · Computer Science 2024-03-22 Krzysztof Lebioda , Viktor Vorobev , Nenad Petrovic , Fengjunjie Pan , Vahid Zolfaghari , Alois Knoll

Self-evolving skill libraries, pioneered by Voyager, let frozen LLM agents accumulate reusable knowledge without weight updates, yet recent evaluation shows that LLM-authored skills deliver $+0.0$pp over no-skill baselines while…

Artificial Intelligence · Computer Science 2026-05-22 Xing Zhang , Yanwei Cui , Guanghui Wang , Ziyuan Li , Wei Qiu , Bing Zhu , Peiyang He

Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through…

This article describes a fully automated, credible autocoding chain for control systems. The framework generates code, along with guarantees of high level functional properties which can be independently verified. It relies on domain…

Systems and Control · Computer Science 2013-08-27 Timothy Wang , Romain Jobredeaux , Heber Herencia , Pierre-Loic Garoche , Arnaud Dieumegard , Eric Feron , Marc Pantel

Code generation aims to produce code that fulfills requirements written in natural languages automatically. Large language Models (LLMs) like ChatGPT have demonstrated promising effectiveness in this area. Nonetheless, these LLMs often fail…

Software Engineering · Computer Science 2025-01-15 Ruwei Pan , Hongyu Zhang , Chao Liu

Modern software systems and products increasingly rely on machine learning models to make data-driven decisions based on interactions with users, infrastructure and other systems. For broader adoption, this practice must (i) accommodate…

Recent progress in large language models (LLMs) has advanced automatic code generation, yet most approaches rely on direct, single-step translation from problem descriptions to code, disregarding structured software engineering practices.…

Software Engineering · Computer Science 2025-10-29 Xing Xing , Wei Wang , Lipeng Ma , Weidong Yang , Junjie Zheng

As a codebase expands over time, its library dependencies can become outdated and require updates to maintain innovation and security. However, updating a library can introduce breaking changes in the code, necessitating significant…

Software Engineering · Computer Science 2025-11-25 Vali Tawosi , Salwa Alamir , Xiaomo Liu , Manuela Veloso