← back

TTHE: Test-Time Harness Evolution

The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies intermediate results, and recovers from failures. Existing approac

https://arxiv.org/abs/2607.08124v1 ↗
Thesis fit
Good fit

Within your typical scope; diligence still required.

Edit thesis
In your usual scope
Idea match Moderate

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

Sector llm, ai

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

Correct facts used on the next screening or memo.

Activity & evidence

Similar baseline plays (YC · idea space)

Arga Labs · Active
Real-world sandboxes to test agents and agent-facing software
founders not scraped yet
ReasonBlocks · Active
The runtime layer that makes AI agents cheaper and more reliable
founders not scraped yet
Tusk · Active
AI agent that generates unit and integration tests
founders not scraped yet
Baserun · Active
Observability and evaluation platform for LLM apps.
founders not scraped yet
Helicone · Acquired
LLM Observability for Developers
founders not scraped yet