Tootfinder

Effects of strain on the stability of the metallic rutile and insulating M1 phases of vanadium dioxide
Peter Mlkvik, Lena Geistlich, Nicola A. Spaldin, Claude Ederer
https://arxiv.org/abs/2510.11480

Effects of strain on the stability of the metallic rutile and insulating M1 phases of vanadium dioxide
We present a systematic density-functional theory study of the effects of strain on the structural and electronic properties in vanadium dioxide (VO$_2$), with particular emphasis on its effect on the relative stability of the metallic rutile and the insulating monoclinic M1 phases. We consider various strain conditions that can be related to epitaxial strain present in VO$_2$ films grown on different lattice planes. Our calculations confirm the dominant role of $c$ axis strain, i.e., along the…

Adversarial Reinforcement Learning for Large Language Model Agent Safety
Zizhao Wang, Dingcheng Li, Vaishakh Keshava, Phillip Wallis, Ananth Balashankar, Peter Stone, Lukas Rutishauser
https://arxiv.org/abs/2510.05442

Adversarial Reinforcement Learning for Large Language Model Agent Safety
Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can manipulate the agent, posing security risks like data leakage. Current defense strategies typically rely on fine-tuning LLM agents on datasets of known attacks. However, the generation of these datasets relies on manually crafted attack patterns, which limits their…