ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

Record

Authors
Wang, Z.; Schiller, N.; Li, H.; et al.
Year
2026
Title
ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
Published in
arXiv
Type
Preprint
DOI
10.48550/arxiv.2605.11086
arXiv
arXiv:2605.11086
Links
https://arxiv.org/abs/2605.11086
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 W7161056873 · DOI 10.48550/arxiv.2605.11086 · arXiv:2605.11086
From the lookup
doi, title (the pages' own wording is under "As cited" below)
Id
wang-2026-exploitgym-can-ai-agents-turn-security

Cited on

As cited

The pages cite this work in one form.

  • Wang, Z., Schiller, N., Li, H., et al. (2026). ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks? arXiv:2605.11086v1. https://arxiv.org/abs/2605.11086

BibLaTeX

@misc{wang-2026-exploitgym-can-ai-agents-turn-security,
  author = {Wang, Z. and Schiller, N. and Li, H. and others},
  title = {{ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?}},
  date = {2026},
  doi = {10.48550/arxiv.2605.11086},
  eprint = {2605.11086},
  eprinttype = {arxiv}
}

Download · JSON with CSL-JSON · the whole bibliography