中文
相关论文

相关论文: app.build: A Production Framework for Scaling Agen…

200 篇论文

The remarkable capabilities of Large Language Model (LLM)-driven agents have enabled sophisticated systems to tackle complex, multi-step tasks, but their escalating costs threaten scalability and accessibility. This work presents the first…

Agentic coding requires agents to effectively interact with runtime environments, e.g., command line interfaces (CLI), so as to complete tasks like resolving dependency issues, fixing system problems, etc. But it remains underexplored how…

人工智能 · 计算机科学 2026-02-12 Yusong Lin , Haiyang Wang , Shuzhe Wu , Lue Fan , Feiyang Pan , Sanyuan Zhao , Dandan Tu

Benchmarks for large language models (LLMs) have progressed from snippet-level function generation to repository-level issue resolution, yet they overwhelmingly target implementation correctness. Software architecture tasks remain…

软件工程 · 计算机科学 2026-03-19 Bassam Adnan , Aviral Gupta , Sreemaee Akshathala , Karthik Vaidhyanathan

Agentic AI systems capable of generating full-stack web applications from natural language prompts ("prompt- to-app") represent a significant shift in software development. However, evaluating these systems remains challenging, as visual…

Scalable AI agents training relies on interactive environments that faithfully simulate the consequences of agent actions. Manually crafted environments are expensive to build, brittle to extend, and fundamentally limited in diversity. A…

人工智能 · 计算机科学 2026-05-11 Yi Liu , TingFeng Hui , Wei Zhang , Li Sun , Ningxin Su , Jian Wang , Sen Su

Production agentic systems make many model calls per user request, and most of those calls are short, structured, and routine. This raises a practical routing question that existing evaluations do not directly answer: which parts of an…

人工智能 · 计算机科学 2026-05-04 Ranit Karmakar , Jayita Chatterjee

Can large language model agents develop industry-level mobile applications? We introduce \textbf{SWE-Bench Mobile}, a benchmark for evaluating coding agents on realistic software engineering tasks derived from a production iOS codebase.…

软件工程 · 计算机科学 2026-02-11 Muxin Tian , Zhe Wang , Blair Yang , Zhenwei Tang , Kunlun Zhu , Honghua Dong , Hanchen Li , Xinni Xie , Guangjing Wang , Jiaxuan You

Large language models are increasingly expected to serve as general-purpose agents that interact with external, stateful tool environments. The Model Context Protocol (MCP) and broader agent skills offer a unified interface for connecting…

LLM-based agents can autonomously accomplish complex tasks across various domains. However, to further cultivate capabilities such as adaptive behavior and long-term decision-making, training on static datasets built from human-level…

机器学习 · 计算机科学 2025-12-24 Yuchen Huang , Sijia Li , Minghao Liu , Wei Liu , Shijue Huang , Zhiyuan Fan , Hou Pong Chan , Yi R. Fung

Agentic AI denotes an architectural transition from stateless, prompt-driven generative models toward goal-directed systems capable of autonomous perception, planning, action, and adaptation through iterative control loops. This paper…

软件工程 · 计算机科学 2026-02-12 Mamdouh Alenezi

As the social environment is growing more complex and collaboration is deepening, factors affecting the healthy development of service ecosystem are constantly changing and diverse, making its governance a crucial research issue. Applying…

人工智能 · 计算机科学 2025-09-03 Deyu Zhou , Yuqi Hou , Xiao Xue , Xudong Lu , Qingzhong Li , Lizhen Cui

AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes…

The transition from Cloud-Native to AI-Native architectures is fundamentally reshaping software engineering, replacing deterministic microservices with probabilistic agentic services. However, this shift renders traditional black-box…

软件工程 · 计算机科学 2026-01-15 Zirui Wang , Guangba Yu , Michael R. Lyu

Large language models (LLMs) like GitHub Copilot and ChatGPT have emerged as powerful tools for code generation, significantly enhancing productivity and accelerating software development. However, existing benchmarks primarily focus on…

软件工程 · 计算机科学 2024-09-27 Yixi Wu , Pengfei He , Zehao Wang , Shaowei Wang , Yuan Tian , Tse-Hsun Chen

Generative AI agents, software systems powered by Large Language Models (LLMs), are emerging as a promising approach to automate cybersecurity tasks. Among the others, penetration testing is a challenging field due to the task complexity…

密码学与安全 · 计算机科学 2024-10-29 Luca Gioacchini , Marco Mellia , Idilio Drago , Alexander Delsanto , Giuseppe Siracusano , Roberto Bifulco

Software development is a complex, multi-phase process traditionally requiring collaboration among individuals with diverse expertise. We propose AgentMesh, a Python-based framework that uses multiple cooperating LLM-powered agents to…

软件工程 · 计算机科学 2025-07-29 Sourena Khanzadeh

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…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Elias Berger , Muhammad Usama , Jan Mehlstäubl , Bernhard Saske , Kristin Paetzold-Byhain

Software vulnerabilities remain a critical security challenge, providing entry points for attackers into enterprise networks. Despite advances in security practices, the lack of high-quality datasets capturing diverse exploit behavior…

密码学与安全 · 计算机科学 2025-11-17 Alireza Lotfi , Charalampos Katsis , Elisa Bertino

Large language models (LLMs) demonstrate strong potential as agents for tool invocation due to their advanced comprehension and planning capabilities. Users increasingly rely on LLM-based agents to solve complex missions through iterative…

人工智能 · 计算机科学 2025-04-17 Peijie Yu , Yifan Yang , Jinjian Li , Zelong Zhang , Haorui Wang , Xiao Feng , Feng Zhang

Reliable Docker-based environment construction is a dominant bottleneck for scaling execution-grounded training and evaluation of software engineering agents. We introduce DockSmith, a specialized agentic Docker builder designed to address…

人工智能 · 计算机科学 2026-04-29 Jiaran Zhang , Luck Ma , Fanqi Wan , Di Qi , Xu Zhao , Jieyi Hou , Zhe Xie , Mengqiang Ren , Xin Wu , Zhewei Huang , Liangyu Chen , Qi Han , Xiangyu Zhang