Across model-harness combinations, agents with comparable competence exhibit markedly different safety outcomes, showing that task capability alone does not guarantee safe execution, and highlighting the need to move beyond risk recognition toward enforcing safety throughout execution.
Abstract
Large language models increasingly act through code, modifying repositories, executing programs, and interacting with services in agent form. Their actions introduce risks that cannot be assessed from generated responses alone. Safety evaluation must verify actual consequences, distinguish harm avoidance from task incapability, and cover realistic workflows. We introduce V$^3$AST-Bench, a benchmark for Verifiable results, Valid interpretation, and Versatile risk coverage of Agent Safety. It comprises 212 risk tasks spanning 18 categories. Dedicated runtime environments verify harm and task outcomes through executable checks over states, records, and artifact behavior, while paired capability twin tasks verify workflow competence. Our experiments span 51 combinations of 11 models and five harnesses, spanning 86,496 trials and over 9 billion tokens of model interaction. Results show that V$^3$AST-Bench remains challenging even for frontier coding agents, as Claude Opus 4.8 with Claude Code still causes verified harm on 20.9% of tasks. Across model-harness combinations, agents with comparable competence exhibit markedly different safety outcomes, showing that task capability alone does not guarantee safe execution. More importantly, even explicit recognition of risks does not reliably prevent harmful actions, revealing a critical gap between risk awareness and safe execution. These findings highlight the need to move beyond risk recognition toward enforcing safety throughout execution.
Mocking is a foundational practice in unit testing, enabling developers to isolate the code under test by replacing real dependencies with simulated alternatives. Automating the generation of mock objects, stubs, and mock assertions has been a long-standing research goal. However, capture-and-replay approaches rely on...
Hao Ning, Jia-Hui Dong, Zhen Yang et al.· 0 citations
As coding agents become more capable, tests remain the primary evidence for judging whether their code is correct. Yet passing available tests does not establish that an implementation satisfies its natural language specification. Reliable validation requires checks that faithfully capture the specification and scenari...
Zhiqing Zhong, Ming-Yu Chen, Ao-Yang Fang et al.· 0 citations
SWE-Nexus enables task construction from validated behavior beyond individual historical changes, a fully automated pipeline that constructs repository-level implementation tasks from test execution from test execution.
Song-Wei Yu, Zi-Qi Miao, Jing-Xuan Xu et al.· 2 citations
When generating verifiable code, natural language requirements are mapped to machine checked code using LLMs and agentic workflows. A crucial component of this pipeline is specification generation (SpecGen), which produces a formal contract against which an agent can prove implementation correctness. Proof generation c...
Srijith Nair, Aditya Vempaty, Jia Liu et al.· 0 citations
Language models are entering systems whose failures matter: vehicles, industrial toolchains, and autonomous agents acting on real infrastructure. At the same time, emerging regulation and safety standards demand not merely safe behavior but evidence of it that a third party can re-check. This survey traces a single arc...
Kamal Essam· International Journal of Ele...· 0 citations
This paper proposes CAST, a systematic testing framework designed to evaluate the compositional safety of LLMs in the domain of malicious code, and demonstrates that CAST systematically exposes severe safety violations in strongly aligned models that resist conventional red-teaming.
Lu Yan, Zhuo Zhang, Xiang-Zhe Xu et al.· Proceedings of the ACM on So...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.