# ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System

arXiv: https://arxiv.org/abs/2509.14589 · HTML: https://mlsanity.com/paper/2509.14589/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2025.

## Built on by (most cited first, 9 of 9)

- [SoK: DARPA's AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned](https://mlsanity.com/paper/2602.07666/) (2026)
- [Patch-to-PoC: A Systematic Study of Agentic LLM Systems for Linux Kernel N-Day Reproduction](https://mlsanity.com/paper/2602.07287/) (2026)
- [PBFuzz: Agentic Directed Fuzzing for PoV Generation](https://mlsanity.com/paper/2512.04611/) (2025)
- [OpenSage: Self-programming Agent Generation Engine](https://mlsanity.com/paper/2602.16891/) (2026)
- [Execution-State-Aware LLM Reasoning for Automated Proof-of-Vulnerability Generation](https://mlsanity.com/paper/2602.13574/) (2026)
- [Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Codebases](https://mlsanity.com/paper/2606.22263/) (2026)
- [Agentic Vulnerability Reasoning on COTS Binaries](https://mlsanity.com/paper/2605.05000/) (2026)
- [Code-Augur: Agentic Vulnerability Detection via Specification Inference](https://mlsanity.com/paper/2606.18619/) (2026)
- [BlueSTAR: Tiered Agentic Architecture for Autonomous Cyber Defense](https://mlsanity.com/paper/2609.11852/) (2026)

## Abstract (arXiv)

We present ATLANTIS, the cyber reasoning system developed by Team Atlanta that won 1st place in the Final Competition of DARPA's AI Cyber Challenge (AIxCC) at DEF CON 33 (August 2025). AIxCC (2023-2025) challenged teams to build autonomous cyber reasoning systems capable of discovering and patching vulnerabilities at the speed and scale of modern software. ATLANTIS integrates large language models (LLMs) with program analysis -- combining symbolic execution, directed fuzzing, and static analysis -- to address limitations in automated vulnerability discovery and program repair. Developed by researchers at Georgia Institute of Technology, Samsung Research, KAIST, and POSTECH, the system addresses core challenges: scaling across diverse codebases from C to Java, achieving high precision while maintaining broad coverage, and producing semantically correct patches that preserve intended behavior. We detail the design philosophy, architectural decisions, and implementation strategies behind ATLANTIS, share lessons learned from pushing the boundaries of automated security when program analysis meets modern AI, and release artifacts to support reproducibility and future research.