小模型高效定位代码漏洞，速度远超大模型。
Antares: Foundation Models for Agentic Vulnerability Localization
- 用两阶段训练法让小模型学会推理和探索代码库
- 30亿参数模型性能接近GPT-5.5，比大模型快200倍
- 单张H100卡15分钟完成500任务评估，成本低于0.002美元/任务
漏洞定位是软件安全的关键步骤，需模型在大型代码库中推理并迭代识别脆弱实现。我们提出Antares，一组紧凑的语言模型（350M、1B和3B参数），用于代理式漏洞定位。基于IBM Granite基础模型，Antares通过两阶段训练流程：先在网络安全推理与仓库探索数据上进行监督微调，再在含漏洞的仓库上利用可验证奖励进行强化学习。在广泛评估中，Antares-3B性能接近GPT-5.5，同时优于参数量大200倍以上的开源模型。该模型家族支持快速、低成本本地推理，在单张H100 GPU上约15分钟完成500任务评估，每任务平均耗时不足2秒，成本低于0.002美元。
原文摘要 · Abstract (English)
Vulnerability localization is a fundamental step in software security, requiring models to reason over large codebases and iteratively identify vulnerable implementations. We present Antares, a family of compact language models (350M, 1B, and 3B parameters) for agentic vulnerability localization. Based on IBM Granite base models, Antares is trained through a two-stage pipeline that combines supervised fine-tuning on cybersecurity reasoning and repository exploration data with reinforcement learning from verifiable rewards over vulnerable repositories. Across extensive evaluations, Antares-3B approaches GPT-5.5 while outperforming open-weight models over 200x larger in size. The Antares family further enables fast, low-cost local inference, completing a full 500-task evaluation sweep in approximately 15 minutes on a single H100 GPU, corresponding to an amortized evaluation time of under 2 seconds and less than $0.002 per task.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。