English
Related papers

Related papers: Empowering Autonomous Debugging Agents with Effici…

200 papers

The deployment of AI models in clinical practice faces a critical challenge: models achieving expert-level performance on benchmarks can fail catastrophically when confronted with real-world variations in medical imaging. Minor shifts in…

Artificial Intelligence · Computer Science 2025-07-09 Lukas Kuhn , Florian Buettner

Recently, the frontier of Large Language Model (LLM) capabilities has shifted from single-turn code generation to agentic software engineering-a paradigm where models autonomously navigate, edit, and test complex repositories. While…

Although large language models (LLMs) have demonstrated impressive coding capabilities, their ability to autonomously build production-scale software from explicit specifications remains an open question. We introduce SWE-AGI, an…

Enterprise IT support is constrained by heterogeneous devices, evolving policies, and long-tail failure modes that are difficult to resolve centrally. We present VIGIL, an edge-extended agentic AI system that deploys desktop-resident agents…

Poorly formulated research problems can compromise the practical relevance of Software Engineering studies by not reflecting the complexities of industrial practice. This vision paper explores the use of artificial intelligence agents to…

Software Engineering · Computer Science 2025-12-16 Anrafel Fernandes Pereira , Maria Teresa Baldassarre , Daniel Mendez , Marcos Kalinowski

A novel Douglas alternating direction implicit (ADI) method is proposed in this work to solve a two-dimensional (2D) heat equation with interfaces. The ADI scheme is a powerful finite difference method for solving parabolic equations, due…

Numerical Analysis · Mathematics 2014-07-01 Shan Zhao

To facilitate the transformation of legacy finite difference implementations into the Devito environment, this study develops an integrated AI agent framework. Retrieval-Augmented Generation (RAG) and open-source Large Language Models are…

Artificial Intelligence · Computer Science 2026-05-27 Yinghan Hou , Zongyou Yang

Large language model (LLM) based coding agents increasingly act as autonomous contributors that generate and merge pull requests, yet their real-world effects on software projects are unclear-especially compared with widely adopted…

Software Engineering · Computer Science 2026-01-28 Shyam Agarwal , Hao He , Bogdan Vasilescu

Despite coding agents' advances in handling increasingly complex tasks, their continued tendency to introduce unintended edits, subtle bugs, and scope drift that slip past code review means developers must still decide how much autonomy to…

Human-Computer Interaction · Computer Science 2026-05-13 Tanjal Shukla , K. J. Kevin Feng , Leijie Wang , Mohammad Rostami , Amy X. Zhang

The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active actors capable of executing shell commands, modifying files, calling APIs, and browsing…

Artificial Intelligence · Computer Science 2026-05-19 Ashwin Aravind

The integration of Large Language Models (LLMs) into software engineering has driven a transition from traditional rule-based systems to autonomous agentic systems capable of solving complex problems. However, systematic progress is…

Software Engineering · Computer Science 2025-10-24 Jiale Guo , Suizhi Huang , Mei Li , Dong Huang , Xingsheng Chen , Regina Zhang , Zhijiang Guo , Han Yu , Siu-Ming Yiu , Pietro Lio , Kwok-Yan Lam

Autonomous AI agents lack traceable accountability mechanisms, creating a fundamental dilemma where systems must either operate as ``downgraded tools'' or risk real-world abuse. This vulnerability stems from the limitations of traditional…

Networking and Internet Architecture · Computer Science 2025-12-22 Zibin Lin , Shengli Zhang , Guofu Liao , Dacheng Tao , Taotao Wang

Vision-language model (VLM) based web agents demonstrate impressive autonomous GUI interaction but remain vulnerable to deceptive interface elements. Existing approaches either detect deception without task integration or document attacks…

Artificial Intelligence · Computer Science 2026-05-12 Yilin Zhang , Yingkai Hua , Chunyu Wei , Xin Wang , Yueguo Chen

With the rapid advancement of low-altitude remote sensing and Vision-Language Models (VLMs), Embodied Agents based on Unmanned Aerial Vehicles (UAVs) have shown significant potential in autonomous tasks. However, current evaluation methods…

Robotics · Computer Science 2025-12-09 Mingning Guo , Mengwei Wu , Jiarun He , Shaoxian Li , Haifeng Li , Chao Tao

LLM-based agents represent a paradigm shift in AI, enabling autonomous systems to plan, reason, and use tools while interacting with dynamic environments. This paper provides the first comprehensive survey of evaluation methods for these…

Artificial Intelligence · Computer Science 2026-04-24 Asaf Yehudai , Lilach Eden , Alan Li , Guy Uziel , Yilun Zhao , Roy Bar-Haim , Arman Cohan , Michal Shmueli-Scheuer

With advances in large language models (LLMs), researchers are creating new systems that can perform AI-driven analytics over large unstructured datasets. Recent work has explored executing such analytics queries using semantic operators --…

Artificial Intelligence · Computer Science 2025-09-04 Matthew Russo , Tim Kraska

Despite recent advancements in Large Language Models (LLMs), complex Software Engineering (SE) tasks require more collaborative and specialized approaches. This concept paper systematically reviews the emerging paradigm of LLM-based…

Software Engineering · Computer Science 2026-01-21 Yongjian Tang , Thomas Runkler

Autonomous code agents built on large language models are reshaping software and AI development through tool use, long-horizon reasoning, and self-directed interaction. However, this autonomy introduces a previously unrecognized security…

Artificial Intelligence · Computer Science 2026-01-30 Xiang Zheng , Yutao Wu , Hanxun Huang , Yige Li , Xingjun Ma , Bo Li , Yu-Gang Jiang , Cong Wang

LLM-based autonomous agents have demonstrated strong capabilities in reasoning, planning, and tool use, yet remain limited when tasks require sustained coordination across roles, tools, and environments. Multi-agent systems address this…

Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad hoc. Existing systems expose traces or generate follow-up feedback, but they do not…

Software Engineering · Computer Science 2026-05-12 Chenyu Zhao , Shenglin Zhang , Yihang Lin , Wenwei Gu , Zhimin Chen , Yongqian Sun , Dan Pei , Chetan Bansal , Saravan Rajmohan , Minghua Ma