English
Related papers

Related papers: BUILD-AND-FIND: An Effort-Aware Protocol for Evalu…

200 papers

We often assume that agent-to-agent interaction will mirror human conversation. However, agents operate fundamentally differently. What if they could develop communication patterns that are more efficient and better aligned with their…

Cryptography and Security · Computer Science 2026-02-03 Marco De Rossi

Commit messages are the atomic level of software documentation. They provide a natural language description of the code change and its purpose. Messages are critical for software maintenance and program comprehension. Unlike documenting…

Software Engineering · Computer Science 2021-12-06 Eman Abdullah AlOmar , Jiaqian Liu , Kenneth Addo , Mohamed Wiem Mkaouer , Christian Newman , Ali Ouni , Zhe Yu

The rapid adoption of AI coding agents is fundamentally shifting software developers' roles from code authors to code reviewers. While developers spend a significant portion of their time reading and comprehending code, the linguistic…

During code reviews, an essential step in software quality assurance, reviewers have the difficult task of understanding and evaluating code changes to validate their quality and prevent introducing faults to the codebase. This is a tedious…

Software Engineering · Computer Science 2024-05-14 Doriane Olewicki , Sarra Habchi , Bram Adams

We introduce PARC, a coding agent for the autonomous and robust execution of long-horizon computational tasks. PARC is built on a hierarchical multi-agent architecture incorporating task planning, execution, and a mechanism that evaluates…

Artificial Intelligence · Computer Science 2025-12-04 Yuki Orimo , Iori Kurata , Hodaka Mori , Ryuhei Okuno , Ryohto Sawada , Daisuke Okanohara

Explanations for AI models in high-stakes domains like medicine often lack verifiability, which can hinder trust. To address this, we propose an interactive agent that produces explanations through an auditable sequence of actions. The…

Artificial Intelligence · Computer Science 2025-11-04 Yuhang Huang , Zekai Lin , Fan Zhong , Lei Liu

Learning by observation can be of key importance whenever agents sharing similar features want to learn from each other. This paper presents an agent architecture that enables software agents to learn by direct observation of the actions…

Artificial Intelligence · Computer Science 2014-02-05 Paulo Roberto Costa , Luís Miguel Botelho

Deep research systems are widely used for multi-step web research, analysis, and cross-source synthesis, yet their evaluation remains challenging. Existing benchmarks often require annotation-intensive task construction, rely on static…

Computation and Language · Computer Science 2026-01-15 Yibo Wang , Lei Wang , Yue Deng , Keming Wu , Yao Xiao , Huanjin Yao , Liwei Kang , Hai Ye , Yongcheng Jing , Lidong Bing

We present Code-QA-Bench, a fully automated framework for synthesizing repository-level code understanding benchmarks that separates genuine code comprehension from documentation recall and pretraining memorization. The framework makes two…

Software Engineering · Computer Science 2026-05-29 Jun Zhang , JianYing Qu , Hanwen Du , Zhongkai Sun , Yehua Yang , Qiao Zhao

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…

Software Engineering · Computer Science 2025-09-23 Abhik Roychoudhury

Large language models have advanced software engineering automation, yet resolving real-world software issues remains difficult because it requires repository-level reasoning, accurate diagnostics, and strong verification signals. Existing…

Software Engineering · Computer Science 2025-11-21 KeFan Li , Mengfei Wang , Hengzhi Zhang , Zhichao Li , Yuan Yuan , Mu Li , Xiang Gao , Hailong Sun , Chunming Hu , Weifeng Lv

Large Language Models (LLMs) can generate Computer-Aided Design (CAD), yet lack physical comprehension required for reliable engineering design. Instead of attempting to implicitly learn physical laws from data, we propose a Hybrid…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Elias Berger , Muhammad Usama , Jan Mehlstäubl , Bernhard Saske , Kristin Paetzold-Byhain

General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse…

Lack of experience, inadequate documentation, and sub-optimal API design frequently cause developers to make mistakes when re-using third-party implementations. Such API misuses can result in unintended behavior, performance losses, or…

Software Engineering · Computer Science 2021-07-13 Sebastian Nielebock , Robert Heumüller , Kevin Michael Schott , Frank Ortmeier

Multimodal Large Language Models (MLLMs) struggle with precise reasoning for structured visuals like charts and diagrams, as pixel-based perception lacks a mechanism for verification. To address this, we propose to leverage derendering --…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Junhong Shen , Mu Cai , Bo Hu , Ameet Talwalkar , David A Ross , Cordelia Schmid , Alireza Fathi

Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…

Software Engineering · Computer Science 2025-01-24 Zezhou Yang , Sirong Chen , Cuiyun Gao , Zhenhao Li , Xing Hu , Kui Liu , Xin Xia

Mining software repositories often requires classifying artifacts like commits, reviews, code lines, or entire repositories into categories. Human labeling is expensive and error-prone; limited context frequently leads to misclassifications…

Software Engineering · Computer Science 2026-05-07 Johannes Härtel

Software engineering agents have shown significant promise in writing code. As AI agents permeate code writing, and generate huge volumes of code automatically -- the matter of code quality comes front and centre. As the automatically…

Software Engineering · Computer Science 2026-04-08 Yuntong Zhang , Zhiyuan Pan , Imam Nur Bani Yusuf , Haifeng Ruan , Ridwan Shariffdeen , Abhik Roychoudhury

Customers interacting with product search engines are increasingly formulating information-seeking queries. Frequently Asked Question (FAQ) retrieval aims to retrieve common question-answer pairs for a user query with question intent.…

Computation and Language · Computer Science 2023-06-07 Zhiyu Chen , Jason Choi , Besnik Fetahu , Oleg Rokhlenko , Shervin Malmasi

Structural understanding of complex visual objects is an important unsolved component of artificial intelligence. To study this, we develop a new technique for the recently proposed Break-and-Make problem in LTRON where an agent must learn…

Artificial Intelligence · Computer Science 2024-10-03 Aaron Walsman , Muru Zhang , Adam Fishman , Ali Farhadi , Dieter Fox