arXiv:2606. 31567v1 Announce Type: cross Abstract: Flaw reporting for deployed AI systems is fundamental to identifying system failures and improving AI safety.
By Shayne Longpre, Elaine Zhu, Carson Ezell, Avijit Ghosh, Sean McGregor, Kevin Paeth, Kevin Klyman, Sayash Kapoor, Rishi Bommasani, Ruth Appel, Gregory Strom, Lauren McIlvenny, Mark M. Jaycox, Peter Slattery, Nathan Butters, Arvind Narayanan, Percy Liang, Alex Pentland
arXiv:2606. 25836v2 Announce Type: replace Abstract: To better assist users with completing challenging tasks, AI agents mediate communications, access data, and interact with different APIs.
By Hyejun Jeong, Dzung Pham, Amir Houmansadr, Eugene Bagdasarian
To better assist users with completing challenging tasks, AI agents mediate communications, access data, and interact with different APIs. Many employers (and even nation-states) already provide their users with this technology.
arXiv:2607. 25379v1 Announce Type: new Abstract: Cyber-capable AI agents combine language models with tools, memory, and execution en- vironments to perform multi-step offensive-security tasks.
By Abu Bakar Siddik
arXiv:2606. 17114v1 Announce Type: cross Abstract: AI agents are increasingly being adopted in enterprise and personal settings with access to emails, databases, documents, and other tools where they can read, update, and disseminate sensitive information.
By Hankyul Baek, Jaewon Noh, Sang Seo, Yongsu Kim, Gabriel Waikin Loh Matienzo, Young Il Kim, Ee Wei Seah, Akriti Vij
arXiv:2607. 05163v1 Announce Type: cross Abstract: AI systems may produce failures after deployment that pre-deployment safety assessments do not anticipate.
By Harleen Kaur Sidhu, Rebecca Scholefield, Nour Annan, Kevin Hernandez, Isabel Nieh Hou, Abdulrahman Alshaikhi, Ze Shen Chin, Rokas Gipi\v{s}kis