中文
相关论文

相关论文: Comment and Control: Hijacking Agentic Workflows v…

200 篇论文

Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into…

人工智能 · 计算机科学 2026-04-06 Yunhao Feng , Yifan Ding , Yingshui Tan , Xingjun Ma , Yige Li , Yutao Wu , Yifeng Gao , Kun Zhai , Yanming Guo

The arrival of large language models (LLMs) capable of multi-step reasoning, tool use, and long-horizon planning has produced a qualitative shift in software engineering. Where earlier code-completion tools such as GitHub Copilot operated…

软件工程 · 计算机科学 2026-04-30 Happy Bhati

Recently, advanced Large Language Models (LLMs) such as GPT-4 have been integrated into many real-world applications like Code Copilot. These applications have significantly expanded the attack surface of LLMs, exposing them to a variety of…

密码学与安全 · 计算机科学 2024-07-24 Huiyu Xu , Wenhui Zhang , Zhibo Wang , Feng Xiao , Rui Zheng , Yunhe Feng , Zhongjie Ba , Kui Ren

This paper introduces a methodology based on agentic workflows for economic research that leverages Large Language Models (LLMs) and multimodal AI to enhance research efficiency and reproducibility. Our approach features autonomous and…

综合经济学 · 经济学 2025-04-15 Herbert Dawid , Philipp Harting , Hankui Wang , Zhongli Wang , Jiachen Yi

Code-capable large language model (LLM) agents are increasingly embedded into software engineering workflows where they can read, write, and execute code, raising the stakes of safety-bypass ("jailbreak") attacks beyond text-only settings.…

密码学与安全 · 计算机科学 2025-10-03 Shoumik Saha , Jifan Chen , Sam Mayers , Sanjay Krishna Gouda , Zijian Wang , Varun Kumar

The increasing adoption of agentic workflows across diverse domains brings a critical need to scalably and systematically evaluate the complex traces these systems generate. Current evaluation methods depend on manual, domain-specific human…

人工智能 · 计算机科学 2025-06-25 Darshan Deshpande , Varun Gangal , Hersh Mehta , Jitin Krishnan , Anand Kannappan , Rebecca Qian

Autonomous coding agents are increasingly integrated into software development workflows, offering capabilities that extend beyond code suggestion to active system interaction and environment management. OpenClaw, a representative platform…

密码学与安全 · 计算机科学 2026-03-23 Fazhong Liu , Zhuoyan Chen , Tu Lan , Haozhen Tan , Zhenyu Xu , Xiang Li , Guoxing Chen , Yan Meng , Haojin Zhu

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…

Cybersecurity has become one of the earliest adopters of agentic AI, as security operations centers increasingly rely on multi-step reasoning, tool-driven analysis, and rapid decision-making under pressure. While individual large language…

密码学与安全 · 计算机科学 2025-12-09 Vaishali Vinay

Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-world execution environments are far from ideal: pop-ups,…

人工智能 · 计算机科学 2026-05-26 Jingwei Sun , Jianing Zhu , Yuanyi Li , Tongliang Liu , Xia HU , Bo Han

Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven construction. We introduce MermaidFlow, a framework that redefines the…

The proliferation of agentic AI coding assistants, including Claude Code, GitHub Copilot, Cursor, and emerging skill-based architectures, has fundamentally transformed software development workflows. These systems leverage Large Language…

密码学与安全 · 计算机科学 2026-01-27 Narek Maloyan , Dmitry Namiot

Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…

密码学与安全 · 计算机科学 2026-03-03 Zhihang Deng , Jiaping Gui , Weinan Zhang

GitHub Actions (GA) has become the de facto tool that developers use to automate software workflows, seamlessly building, testing, and deploying code. Yet when GA fails, it disrupts development, causing delays and driving up costs.…

Autonomous coding agents, powered by large language models (LLMs), are increasingly being adopted in the software industry to automate complex engineering tasks. However, these agents are prone to a wide range of misbehaviors, such as…

软件工程 · 计算机科学 2026-02-23 Rahul Nanda , Chandra Maddila , Smriti Jha , Euna Mehnaz Khan , Matteo Paltenghi , Satish Chandra

Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an…

密码学与安全 · 计算机科学 2026-05-13 Hongwei Yao , Yiming Liu , Yiling He , Bingrun Yang

Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this…

密码学与安全 · 计算机科学 2026-03-30 Shiping Chen , Qin Wang , Guangsheng Yu , Xu Wang , Liming Zhu

GitHub Continuous Integration (CI) workflows increasingly integrate Large Language Models (LLMs) to automate review, triage, content generation, and repository maintenance. This creates a new attack surface: externally controllable workflow…

密码学与安全 · 计算机科学 2026-05-08 Bonan Ruan , Yeqi Fu , Chuqi Zhang , Jiahao Liu , Jun Zeng , Zhenkai Liang

Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. These agent-based systems…

密码学与安全 · 计算机科学 2024-10-23 Xiaohan Fu , Shuheng Li , Zihan Wang , Yihao Liu , Rajesh K. Gupta , Taylor Berg-Kirkpatrick , Earlence Fernandes

Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or booking travel. While these integrations unlock powerful capabilities, they also create new and…

密码学与安全 · 计算机科学 2026-04-22 Jonathan Evertz , Merlin Chlosta , Lea Schönherr , Thorsten Eisenhofer