# TitanCA: Lessons from Orchestrating LLM Agents to Discover 100+ CVEs

arXiv: https://arxiv.org/abs/2604.17860 · HTML: https://mlsanity.com/paper/2604.17860/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 3 of its 5 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 3 of 3)

- [Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents](https://mlsanity.com/paper/2505.10961/) (2025)
- [Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?](https://mlsanity.com/paper/2507.21817/) (2025)
- [Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework](https://mlsanity.com/paper/2510.01002/) (2025)

## Built on by (most cited first, 2 of 2)

- [Harmonizing AI Safety Thresholds](https://mlsanity.com/paper/2607.16112/) (2026)
- [The History Is the Detector: Executing CVE Patch History, End-to-End](https://mlsanity.com/paper/2609.05335/) (2026)

## Abstract (arXiv)

Software vulnerabilities remain one of the most persistent threats to modern digital infrastructure. While static application security testing (SAST) tools have long served as the first line of defense, they suffer from high false-positive rates. This article presents TitanCA, a collaborative project between Singapore Management University and GovTech Singapore that orchestrates multiple large language model (LLM)-powered agents into a unified vulnerability discovery pipeline. Applied in open-source software, TitanCA has discovered 203 confirmed zero-day vulnerabilities and yielded 118 CVEs. We describe the four-module architecture, i.e., matching, filtering, inspection, and adaptation, and share key lessons from building and deploying an LLM-based vulnerability discovery solution in practice.