ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense
This addresses the need to assess LLM agents for proactive cyberdefense in software engineering, but it is incremental as it focuses on benchmarking existing models without proposing new methods.
The paper tackled the problem of evaluating LLM agents' ability to find and patch security vulnerabilities by introducing ZeroDayBench, a benchmark with 22 novel critical vulnerabilities, and found that frontier LLMs like GPT-5.2, Claude Sonnet 4.5, and Grok 4.1 are not yet capable of autonomously solving these tasks.
Large language models (LLMs) are increasingly being deployed as software engineering agents that autonomously contribute to repositories. A major benefit these agents present is their ability to find and patch security vulnerabilities in the codebases they oversee. To estimate the capability of agents in this domain, we introduce ZeroDayBench, a benchmark where LLM agents find and patch 22 novel critical vulnerabilities in open-source codebases. We focus our efforts on three popular frontier agentic LLMs: GPT-5.2, Claude Sonnet 4.5, and Grok 4.1. We find that frontier LLMs are not yet capable of autonomously solving our tasks and observe some behavioral patterns that suggest how these models can be improved in the domain of proactive cyberdefense.