Skip to content
NewA calmer, faster ZeroHour

Agents keep finding exploits after they stop, SCoRe study finds

Original title: Stopping Is Not the Limit: Understanding and Eliciting Agent Capability in Long-Horizon Vulnerability Exploitation

arXiv cs.CRby Deokhyung Kang ()1 min read1
AI summary · x-ai/grok-4.7Summaries by Vani AI

With SCoRe, MiMo reached 67.0% capability coverage at 2,000 turns, above a 58.6% GPT-5.5 reference.

A paper on ExploitBench tests whether language-model agents can keep producing verified exploits after their first stop. DeepSeek-V4-Flash-0731 and MiMo-V2.6-Pro gained further verified successes, but returns fell as stop responses and impossibility judgments accumulated. SCoRe compacts context at stop bursts and treats those judgments as unproven, beating summary-based continuation and other context-management baselines.

Unconfirmed: Capability scores are benchmark results, not evidence of attacks outside ExploitBench.

Key facts
  • Additional verified gains appear after the first stop, then diminish.
  • MiMo scored 32.4% under the original stopping policy.
  • The GPT-5.5 comparison uses ExploitBench's 300-turn reference results.
  • SCoRe marks retained impossibility judgments as unproven.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at arxiv.org

Vulnerability exploitation tests whether language model agents can develop working exploits from known software flaws. Sequential test-time scaling can improve exploitation performance, but larger budgets do not ensure sustained exploration: agents often stop with budget remaining. Yet what happens when execution continues beyond stopping remains underexplored.

arXiv cs.CR

By Deokhyung Kang · arxiv.org

Read the full article at arXiv cs.CR

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.