Large language model (LLM) agents are increasingly capable of supporting scientific workflows, but their capabilities across diverse research activities remain difficult to assess systematically. Existing benchmarks often focus on selected scientific capabilities or task types, limiting a comprehensive characterization...
Tian-Yun Zhong, Wei Wang, Jia-Ling Li et al.· 0 citations
ReCode is introduced, a compositional budget-efficient attack that combines desensitization rewriting with two effective low-cost primitives identified by Fair-ASR, to provide a comparable evaluation basis for black-box jailbreak attacks under shared target-call budgets B.
This work introduces \textsc{JailbreakSkill}, a skill-centric framework for scaling automated red-teaming through reusable and continuously evolving attack capabilities, which packages existing attack strategies into modular, agent-ready skills that can be directly reused and adaptively selected across tasks and target...
Xiaoyu Wen, Jiajia Li, Zhida He et al.· 2 citations
Evaluation of 19 multimodal large language models shows that current MLLMs still cannot reliably make justified and evidence-bounded inferences from experimental results, which is an essential capability in real scientific discovery.
Tao Han, Yucheng Zhang, Jing-Hang Wang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
