Metraipolis › archive › dc_ba9152b00129
DoGNAVY-Exploit: Harnessing Parallel Open-Weight Agents for Stage-Aware Vulnerability Exploitation — arXiv:2611.04196
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04196
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:27:43.451Z
- SHA-256 of the archived text
a3d61c1908a4116d24146be91e2c9ca76a47a4d7126694f47cd6bd1eeb38cae3- Stable URL of this page
https://metraipolis.com/documento/dc_ba9152b00129
How to cite
DoGNAVY-Exploit: Harnessing Parallel Open-Weight Agents for Stage-Aware Vulnerability Exploitation — arXiv:2611.04196 — arXiv (en), https://arxiv.org/abs/2611.04196 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ba9152b00129 (Metraipolis archive dc_ba9152b00129, sha256 a3d61c1908a4116d24146be91e2c9ca76a47a4d7126694f47cd6bd1eeb38cae3)
BibTeX
@misc{dcba9152b00129,
title = {DoGNAVY-Exploit: Harnessing Parallel Open-Weight Agents for Stage-Aware Vulnerability Exploitation — arXiv:2611.04196},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04196},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ba9152b00129; sha256 a3d61c1908a4116d24146be91e2c9ca76a47a4d7126694f47cd6bd1eeb38cae3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04196. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Frontier LLM agents can turn known vulnerabilities into working exploits, but are costly and often access-restricted due to their potential for malicious use. Open-weight models offer a more accessible alternative, but struggle to maintain progress across long exploitation chains. They also often fail to apply relevant security knowledge at the appropriate stage and in the right context to identify and evaluate promising attack directions. To address these limitations, we propose DoGNAVY-Exploit, a multi-agent harness built around two complementary designs: stage-aware decomposition with progressive expert knowledge disclosure, and hierarchical orchestration with parallel exploration. Specifically, DoGNAVY-Exploit uses configurable milestones to recast long-horizon exploitation as short, verifiable capability transitions and provides only the knowledge relevant to each stage. Within each milestone, a hierarchical architecture separates strategic planning from parallel execution: a planner proposes diverse attack routes, executors test them concurrently, and a controller accepts progress only when supported by runtime evidence. A shared structured memory consolidates verified facts, artifacts, replay steps, and failed routes across branches, allowing agents to build on collective progress and carry validated knowledge into subsequent milestones. In controlled benchmark environments, DoGNAVY-Exploit with GLM-5.2 achieves 97.5% Pass@1 on Cybench, and 97.5% zero-day and 100% one-day Pass@1 on CVE-Bench. On ExploitGym, it solves 79 tasks with GLM-5.2 and 157 with GLM-5.3, while the corresponding public Claude Code baselines solve 39 and 130 tasks, respectively. Ablation results further demonstrate that the stage-aware orchestration, expert knowledge, parallel exploration, and memory designs can substantially improve the exploitation capabilities of open-weight agents. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.04196 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-04T12:26:47.132Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).