Antares: Foundation Models for Agentic Vulnerability Localization
Ranking
Overall
71
Content
75
Popularity
61
Observed public metrics from 1 member.
Merged summary
TL;DR - Antares is a family of compact (350M/1B/3B) language models built on IBM Granite and trained specifically for agentic vulnerability localization, showing that small, task-specialized models can rival frontier LLMs on security code reasoning at a tiny fraction of the cost.
- Two-stage training pipeline: supervised fine-tuning on cybersecurity reasoning plus repository-exploration data, followed by reinforcement learning from verifiable rewards over vulnerable repositories.
- Antares-3B reportedly approaches GPT-5.5 performance while outperforming open-weight models more than 200x larger.
- Efficiency claim: a full 500-task evaluation sweep runs in ~15 minutes on a single H100, under 2 seconds and less than $0.002 per task amortized.
- Targets the agentic setting — iteratively navigating large codebases to pinpoint vulnerable implementations, rather than single-shot classification of isolated snippets.
Sources (1)
Antares: Foundation Models for Agentic Vulnerability Localization
Public signals
Hugging Face upvotes 3
TL;DR - Antares is a family of compact (350M/1B/3B) language models built on IBM Granite and trained specifically for agentic vulnerability localization, showing that small, task-specialized models can rival frontier LLMs on security code reasoning at a tiny fraction of the cost.
- Two-stage training pipeline: supervised fine-tuning on cybersecurity reasoning plus repository-exploration data, followed by reinforcement learning from verifiable rewards over vulnerable repositories.
- Antares-3B reportedly approaches GPT-5.5 performance while outperforming open-weight models more than 200x larger.
- Efficiency claim: a full 500-task evaluation sweep runs in ~15 minutes on a single H100, under 2 seconds and less than $0.002 per task amortized.
- Targets the agentic setting — iteratively navigating large codebases to pinpoint vulnerable implementations, rather than single-shot classification of isolated snippets.