English
Related papers

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

200 papers

As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Reward hacking naturally arises in this setup, as the agent optimizes for passing tests…

Software Engineering · Computer Science 2026-05-21 Bingchen Zhao , Dhruv Srikanth , Yuxiang Wu , Zhengyao Jiang

Large vision-language models have significantly advanced GUI agents, enabling executable interaction across web, mobile, and desktop interfaces. Yet these gains largely rely on a forgiving region-tolerant paradigm, where many nearby pixels…

Artificial Intelligence · Computer Science 2026-05-18 Jingxuan Wei , Xi Bai , Shan Liu , Caijun Jia , Zheng Sun , Xinglong Xu , Siyuan Li , Linzhuang Sun , Bihui Yu , Conghui He , Cheng Tan

To integrate seamlessly into real-world software engineering, Code Agents must evolve from passive instruction followers into proactive collaborative partners. However, current evaluation paradigms predominantly reward "guessing" user…

Software Engineering · Computer Science 2026-03-03 Jialin Li , Yuan Wu , Yi Chang

AI agents today have passwords but no permission slips. They execute tool calls (fund transfers, database queries, shell commands, sub-agent delegation) with no standard mechanism to enforce authorization before the action executes. Current…

Cryptography and Security · Computer Science 2026-03-24 Uchi Uchibeke

Autonomous web agents solve complex browsing tasks, yet existing benchmarks measure only whether an agent finishes a task, ignoring whether it does so safely or in a way enterprises can trust. To integrate these agents into critical…

Artificial Intelligence · Computer Science 2026-03-03 Ido Levy , Ben Wiesel , Sami Marreed , Alon Oved , Avi Yaeli , Segev Shlomov

The rise of autonomous AI agents exposes a fundamental flaw in API-centric architectures: probabilistic systems directly execute state mutations without sufficient context, coordination, or safety guarantees. We introduce OpenKedge, a…

Artificial Intelligence · Computer Science 2026-04-13 Jun He , Deying Yu

With the rapidly increasing capabilities and adoption of code agents for AI-assisted coding, safety concerns, such as generating or executing risky code, have become significant barriers to the real-world deployment of these agents. To…

Software Engineering · Computer Science 2024-11-13 Chengquan Guo , Xun Liu , Chulin Xie , Andy Zhou , Yi Zeng , Zinan Lin , Dawn Song , Bo Li

Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs alone do not carry. Safety evaluations, however, overwhelmingly measure…

Artificial Intelligence · Computer Science 2026-02-20 Arnold Cartagena , Ariane Teixeira

Large language models (LLMs) are increasingly deployed as agents in various contexts by providing tools at their disposal. However, LLM agents can exhibit unpredictable behaviors, including taking undesirable and/or unsafe actions. In order…

Artificial Intelligence · Computer Science 2025-10-27 Ilija Lichkovski , Alexander Müller , Mariam Ibrahim , Tiwai Mhundwa

Agents powered by large language models (LLMs) are increasingly adopted in the software industry, contributing code as collaborators or even autonomous developers. As their presence grows, it becomes important to assess the current…

Software Engineering · Computer Science 2026-02-12 Qixing Zhou , Jiacheng Zhang , Haiyang Wang , Rui Hao , Jiahe Wang , Minghao Han , Yuxue Yang , Shuzhe Wu , Feiyang Pan , Lue Fan , Dandan Tu , Zhaoxiang Zhang

As autonomous coding agents become capable of handling increasingly long-horizon tasks, they have gradually demonstrated the potential to complete end-to-end software development. Although existing benchmarks have recently evolved from…

Software Engineering · Computer Science 2026-05-19 Qingnan Ren , Shun Zou , Shiting Huang , Ziao Zhang , Kou Shi , Zhen Fang , Yiming Zhao , Yu Zeng , Qisheng Su , Lin Chen , Yong Wang , Zehui Chen , Xiangxiang Chu , Feng Zhao

Agentic coding tools, such as OpenAI Codex, Claude Code, and Cursor, are transforming the software engineering landscape. These AI-powered systems function as autonomous teammates capable of planning and executing complex development tasks.…

Software Engineering · Computer Science 2025-11-10 Kosei Horikawa , Hao Li , Yutaro Kashiwa , Bram Adams , Hajimu Iida , Ahmed E. Hassan

Agent systems often decompose a task across multiple roles, but these roles are typically specified by prompts rather than enforced by access controls. Without enforcement, a team pass rate can mask whether agents actually coordinated or…

Large language model agents increasingly operate through an intermediate skill layer that mediates between user intent and concrete task execution. This layer is widely treated as an organizational abstraction, but we argue it is also a…

Artificial Intelligence · Computer Science 2026-05-14 Shawn Li , Chenxiao Yu , Han Wang , Wei Yang , Ryan Rossi , Franck Dernoncourt , Xiyang Hu , Philip Yu , Chaowei Xiao , Huan Zhang , Yue Zhao

A general-purpose language model that answers a harmful question returns text; a coding model that complies with a malicious request can return a working weapon -- a keylogger, a ransomware stub, an exploit that runs as written. This…

Cryptography and Security · Computer Science 2026-05-28 Richard J. Young , Gregory D. Moody

AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually experience misalignment. We present an observational study of…

Software Engineering · Computer Science 2026-05-29 Ningzhi Tang , Chaoran Chen , Gelei Xu , Yiyu Shi , Yu Huang , Collin McMillan , Tao Dong , Toby Jia-Jun Li

Large language models can generate scientific simulation code, but the generated code silently fails on most non-textbook problems. We show that classical mathematical validation -- well-posedness, convergence, and error certification --…

Software Engineering · Computer Science 2026-03-30 Chengshuai Yang

AI agents increasingly act through external tools: they query databases, execute shell commands, read and write files, and send network requests. Yet in most current agent stacks, model-generated tool calls are handed to the execution layer…

Cryptography and Security · Computer Science 2026-03-16 Aojie Yuan , Zhiyuan Su , Yue Zhao

Random rules improve a coding agent's task performance as much as expert-curated ones (both $+13.8$pp on a discriminative subset of SWE-bench Verified), and in our data every individually beneficial rule is a negative constraint ("do not…

Artificial Intelligence · Computer Science 2026-05-29 Xing Zhang , Guanghui Wang , Yanwei Cui , Wei Qiu , Ziyuan Li , Bing Zhu , Peiyang He

Unlike traditional automation tools or static LLM-based systems, agents combine decision-making and tool utilization to accomplish complex tasks, showing great potential in software engineering. However, existing studies largely focus on…

Software Engineering · Computer Science 2025-11-04 Zhuowen Yin , Cuifeng Gao , Chunsong Fan , Wenzhang Yang , Yinxing Xue , Lijun Zhang