DoGNAVY-Exploit: Harnessing Parallel Open-Weight Agents for Stage-Aware Vulnerability Exploitation

Yuxuan Wang, Dadi Guo, Weijie Guo, Zikai Xu, Chen Lu, Yizhe Zhuang, Peng Huang, Yuejin Xie, Guopeng Lin, Xuangan Xiao, Shipei Qu, Dongrui LiuarXiv 2026 · arXiv

TL;DR

DoGNAVY-Exploit is a multi-agent framework that enables open-weight LLMs to perform complex, multi-step vulnerability exploitation at a level previously reserved for restricted, high-cost proprietary models. By using stage-aware decomposition and parallel exploration, it achieves frontier-level performance—solving 97.5% of Cybench tasks—while being up to 4.5x more cost-effective than closed-source alternatives.

What Problem Does This Paper Address?

Turning a known vulnerability into a working exploit is a "long-horizon" task. It requires a chain of logical steps: reproducing the bug, discovering "primitives" (like the ability to read or write arbitrary memory), and finally composing those primitives into a payload that achieves code execution.

While frontier models like GPT-4 or Claude 3.5 are capable of this, they face two major hurdles:

  1. Cost and Access: These models are expensive and often restricted by safety guardrails that block legitimate cybersecurity research.
  2. The Long-Horizon Dilemma: Even powerful models struggle to maintain progress over long trajectories. They often get stuck in unproductive loops, lose track of the global goal, or fail to apply the right security technique at the right time.

Open-weight models (like the GLM series) offer a more accessible alternative but typically lack the "stamina" and specialized reasoning to handle these complex chains without a specialized harness.

Figure 1: Key challenges in LLM-based vulnerability exploitation. Agents must identify the correct exploit path through long-horizon exploration, while also selecting and applying the right security technique at the appropriate exploitation stage.

Methods

The authors introduce DoGNAVY-Exploit, a multi-agent system designed to overcome these limitations through four key architectural pillars:

  • Stage-Aware Decomposition: Instead of one long prompt, the task is broken into three distinct milestones:
  • Vulnerability-centric: Reproducing the bug and understanding the environment.
  • Primitive discovery: Probing for capabilities like arbitrary read/write.
  • Exploit-chain construction: Composing discovered primitives into a final attack.
  • Hierarchical Orchestration: The system separates strategy from execution. A Route Planner proposes multiple attack hypotheses, while Parallel Executors test them concurrently. A Controller then evaluates the evidence before allowing the system to move to the next stage.
  • Progressive Expert Knowledge Disclosure: Rather than overwhelming the agent with every security technique at once, the system only provides knowledge relevant to the current stage and the agent's specific role (e.g., a planner gets strategy guides, while an executor gets payload construction tips).
  • Shared Structured Memory: To prevent "context bloat," the system doesn't pass raw logs. Instead, it maintains a structured memory of verified facts, falsified assumptions, and reusable artifacts (like memory addresses or scripts), summarized into a "State Capsule."
Figure 2: Overview of DoGNAVY-Exploit. The framework decomposes exploitation into milestone-driven stages and, within each stage, coordinates hierarchical planning and parallel execution with stage- and role-specific knowledge. A shared structured memory consolidates verified progress, failed assumptions, and reusable artifacts across routes and stages.

Datasets

The framework was evaluated on three diverse benchmarks:

  • Cybench: 40 professional-level Capture-the-Flag (CTF) tasks covering general cybersecurity problem-solving.
  • CVE-Bench: Real-world web application vulnerabilities derived from critical CVEs, tested in both "zero-day" (localization required) and "one-day" (info provided) settings.
  • ExploitGym: A large-scale, challenging benchmark focused on low-level binary exploitation across userspace programs, the V8 engine, and the Linux kernel.

Key Insights and Ideas

  • Parallelism as Robustness: In exploitation, many paths lead to dead ends. By exploring multiple routes concurrently, DoGNAVY-Exploit is far less likely to get "trapped" in a local subtask compared to single-threaded agents.
  • Context Management is King: The "State Capsule" approach proves that for long-horizon tasks, a concise summary of validated progress is more valuable than a massive history of every command ever run.
  • The "Right Technique, Right Stage" Principle: Weaker models often possess the necessary knowledge but apply it at the wrong time. Forcing a stage-gate process (milestones) ensures the model doesn't try to build a complex payload before it even understands the basic bug.

Key Results

DoGNAVY-Exploit, powered by the open-weight GLM-5.2 and GLM-5.3 models, delivered impressive numbers:

  • Cybench: Achieved 97.5% Pass@1, outperforming the default ReAct baseline (82.5%) and rivaling proprietary frontier results.
  • CVE-Bench: Reached 97.5% accuracy on zero-day tasks and 100% on one-day tasks.
  • ExploitGym: Solved 157 tasks with GLM-5.3, significantly outperforming the Claude Code baseline (130 tasks).
  • Cost Efficiency: This is the standout result. The GLM-5.2 configuration costs only $4.80 per case. As shown in the figures below, it achieves a much higher "yield" of successful exploits per dollar spent compared to closed-source models.

Cost-exploitation performance on ExploitGym. Successful exploits per $1,000 on ExploitGym.

Limitations and Future Work

The authors noted a specific failure mode in userspace targets: agents would often capture a "flag" by finding a different vulnerability than the one intended (off-target captures). This suggests that in broad attack surfaces, directing the agent to a specific bug remains a challenge.

Future work will likely focus on the "co-evolution" of these multi-agent harnesses with even more specialized, domain-specific models to further push the boundaries of automated offensive security.

Summary updated

Abstract

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.
BibTeX
@misc{wang2026dognavy,
  author = {Yuxuan Wang and Dadi Guo and Weijie Guo and Zikai Xu and Chen Lu and Yizhe Zhuang and Peng Huang and Yuejin Xie and Guopeng Lin and Xuangan Xiao and Shipei Qu and Dongrui Liu},
  title = {{DoGNAVY-Exploit: Harnessing Parallel Open-Weight Agents for Stage-Aware Vulnerability Exploitation}},
  year = {2026},
  eprint = {2611.04196},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.04196},
}
Figure