English
Related papers

Related papers: Overeager Coding Agents: Measuring Out-of-Scope Ac…

200 papers

Background: Agent skills are increasingly deployed as modular, reusable capability units in AI agent systems. Medical research agent skills require safeguards beyond general-purpose evaluation, including scientific integrity, methodological…

Artificial Intelligence · Computer Science 2026-04-23 Yingyong Hou , Xinyuan Lao , Huimei Wang , Qianyu Yao , Wei Chen , Bocheng Huang , Fei Sun , Yuxian Lv , Weiqi Lei , Xueqian Wen , Pengfei Xia , Zhujun Tan , Shengyang Xie

Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluate general-purpose performance~(e.g., WebArena) or safety against malicious actions~(e.g.,…

Cryptography and Security · Computer Science 2026-04-09 Guruprasad Viswanathan Ramesh , Asmit Nayak , Basieem Siddique , Kassem Fawaz

Computer-using agents have shown strong potential to boost human productivity and enable new application forms across platforms. While recent advances have led to usable applications, existing benchmarks fail to account for the internal…

Evaluating Large Language Models (LLMs) on repository-level feature implementation is a critical frontier in software engineering. However, establishing a benchmark that faithfully mirrors realistic development scenarios remains a…

Computation and Language · Computer Science 2026-02-19 Haorui Chen , Chengze Li , Jia Li

Decompilation -- recovering source code from compiled binaries -- is essential for security analysis, malware reverse engineering, and legacy software maintenance. However, existing decompilers produce code that often fails to compile or…

Software Engineering · Computer Science 2026-05-05 Yifan Zhang , Xiaohan Wang , Yueke Zhang , Yu Huang , Kevin Leach

Code review, which aims at ensuring the overall quality and reliability of software, is a cornerstone of software development. Unfortunately, while crucial, Code review is a labor-intensive process that the research community is looking to…

Software Engineering · Computer Science 2024-09-26 Xunzhu Tang , Kisub Kim , Yewei Song , Cedric Lothritz , Bei Li , Saad Ezzini , Haoye Tian , Jacques Klein , Tegawende F. Bissyande

Vibe coding is a new programming paradigm in which human engineers instruct large language model (LLM) agents to complete complex coding tasks with little supervision. Although vibe coding is increasingly adopted, are its outputs really…

Software Engineering · Computer Science 2026-02-18 Songwen Zhao , Danqing Wang , Kexun Zhang , Jiaxuan Luo , Zhuo Li , Lei Li

Autonomous agents that accomplish complex computer tasks with minimal human interventions have the potential to transform human-computer interaction, significantly enhancing accessibility and productivity. However, existing benchmarks…

Computer-use agents (CUAs) automate on-screen work, as illustrated by GPT-5.4 and Claude. Yet their reliability on complex, low-frequency interactions is still poor, limiting user trust. Our analysis of failure cases from advanced models…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Miaosen Zhang , Xiaohan Zhao , Zhihong Tan , Zhou Huoshen , Yijia Fan , Yifan Yang , Kai Qiu , Bei Liu , Justin Wagle , Chenzhong Yin , Mingxi Cheng , Ji Li , Qi Dai , Chong Luo , Xu Yang , Xin Geng , Baining Guo

The advancements of large language models (LLMs) have piqued growing interest in developing LLM-based language agents to automate scientific discovery end-to-end, which has sparked both excitement and skepticism about their true…

Existing agent safety benchmarks report binary accuracy, conflating early intervention with post-mortem analysis. A detector that flags a violation at step 8 enables intervention; one that reports it at step 48 provides only forensic value.…

Deploying agentic AI in regulated contexts requires principled reasoning about two design dimensions: agency (what the system can do) and autonomy (how much it acts without human involvement). Though often treated independently, they are…

Artificial Intelligence · Computer Science 2026-05-13 Damir Safin , Dian Balta

With the rapid progress of multimodal large language models, operating system (OS) agents become increasingly capable of automating tasks through on-device graphical user interfaces (GUIs). However, most existing OS agents are designed for…

Computation and Language · Computer Science 2026-04-06 Zheng Wu , Heyuan Huang , Xingyu Lou , Xiangmou Qu , Pengzhou Cheng , Zongru Wu , Weiwen Liu , Weinan Zhang , Jun Wang , Zhaoxiang Wang , Zhuosheng Zhang

Large language model agents are increasingly expected to perform operational work: calling APIs, manipulating files, assembling workflows, and acting inside enterprise systems. Yet the tool layer on which this execution depends is still…

Software Engineering · Computer Science 2026-05-28 Swanand Rao

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…

Computation and Language · Computer Science 2026-05-22 Asaf Yehudai , Lilach Eden , Michal Shmueli-Scheuer

Large language model agents are increasingly envisioned as always-on personal assistants with access to anything relevant in the user's digital world. Yet current systems operate over only narrow slices of that world, limiting…

Artificial Intelligence · Computer Science 2026-05-26 Yusong Lin , Xinyuan Liang , Haiyang Wang , Qipeng Gu , Siqi Cheng , Jiangui Chen , Shuzhe Wu , Feiyang Pan , Lue Fan , Sanyuan Zhao , Dandan Tu

Computer-using agents (CUAs), which can autonomously control computers to perform multi-step actions, might pose significant safety risks if misused. However, existing benchmarks mainly evaluate LMs in chatbots or simple tool use. To more…

Cryptography and Security · Computer Science 2025-09-25 Aaron Xuxiang Tian , Ruofan Zhang , Janet Tang , Ji Wang , Tianyu Shi , Jiaxin Wen

Recent neural models of code, such as OpenAI Codex and AlphaCode, have demonstrated remarkable proficiency at code generation due to the underlying attention mechanism. However, it often remains unclear how the models actually process code,…

Software Engineering · Computer Science 2024-08-30 Matteo Paltenghi , Rahul Pandita , Austin Z. Henley , Albert Ziegler

Computer-use agent (CUA) frameworks, powered by large language models (LLMs) or multimodal LLMs (MLLMs), are rapidly maturing as assistants that can perceive context, reason, and act directly within software environments. Among their most…

Cryptography and Security · Computer Science 2025-10-13 Weidi Luo , Qiming Zhang , Tianyu Lu , Xiaogeng Liu , Bin Hu , Hung-Chun Chiu , Siyuan Ma , Yizhe Zhang , Xusheng Xiao , Yinzhi Cao , Zhen Xiang , Chaowei Xiao

Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks by dynamically utilising external software components. However, these tools must be implemented in advance by human developers,…

Computation and Language · Computer Science 2025-06-02 Georg Wölflein , Dyke Ferber , Daniel Truhn , Ognjen Arandjelović , Jakob Nikolas Kather
‹ Prev 1 8 9 10 Next ›