Record
- Authors
- Kutasov, J.; Loughridge, C.; Sun, Y.; Sleight, H.; Shlegeris, B.; Tracy, T.; Benton, J.
- Year
- 2025
- Title
- Evaluating Control Protocols for Untrusted AI Agents
- Published in
- arXiv
- Type
- Preprint
- DOI
- 10.48550/arxiv.2511.02997
- arXiv
- arXiv:2511.02997
- Links
- https://arxiv.org/abs/2511.02997
- Our note
- none yet
- Verification
- verified: its identifier resolves to a record with the same title and author (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W7104293242 · DOI 10.48550/arxiv.2511.02997 · arXiv:2511.02997 - From the lookup
- doi, title (the pages' own wording is under "As cited" below)
- Id
kutasov-2025-evaluating-control-protocols-untrusted-ai-agents
Cited on
- Strengthening Red Teams: A Modular Scaffold for Control Evaluations for Sections 1 to 3 read status: not stated
As cited
The pages cite this work in one form.
-
Kutasov, J., Loughridge, C., Sun, Y., Sleight, H., Shlegeris, B., Tracy, T., and Benton, J. (2025). Evaluating control protocols for untrusted AI agents. arXiv:2511.02997 (v1, 4 November 2025; abstract and Sections 1 to 3 read). https://arxiv.org/abs/2511.02997
BibLaTeX
@misc{kutasov-2025-evaluating-control-protocols-untrusted-ai-agents,
author = {Kutasov, J. and Loughridge, C. and Sun, Y. and Sleight, H. and Shlegeris, B. and Tracy, T. and Benton, J.},
title = {{Evaluating Control Protocols for Untrusted AI Agents}},
date = {2025},
doi = {10.48550/arxiv.2511.02997},
eprint = {2511.02997},
eprinttype = {arxiv}
}