← back

DREA: Decoupled Reasoning and Exploration Agents for Repository-Level Vulnerabil

Large language models (LLMs) are increasingly applied to vulnerability detection due to their strong code comprehension capabilities, but most existing approaches rely on isolated functions or context extracted by fixed program-analysis rul

https://arxiv.org/abs/2607.13439v1 ↗
Thesis fit
Good fit

Within your typical scope; diligence still required.

Edit thesis
In your usual scope
Idea match Light

How close the company’s idea is to your thesis statement

Sector agents, llm

Overlap with sectors you care about

Geography Unknown

Location unknown — scores 0

Your thesis: “We back exceptional technical founders building AI-first products and infrastructure, deploying $100K checks within 24 hours.”

Founder → stable Traction → stable Idea vs market → stable
Generate memo
Add / edit details

Correct facts used on the next screening or memo.

Similar baseline plays (YC · idea space)

Envariant · Active
Interpretability and reasoning infra for foundation models.
founders not scraped yet
Helicone · Acquired
LLM Observability for Developers
founders not scraped yet
compliant-llm · Active
Detect every data leak into third-party GenAI tools
founders not scraped yet
LunaSec · Inactive
An Open Source dependency security tool that is smarter than the rest
founders not scraped yet
Veria Labs · Active
Continuous AI pentesting that finds and fixes vulnerabilities
founders not scraped yet