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.
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
▸ Add / edit details
Correct facts used on the next screening or memo.
People
J
Jun Nie
1.0
low confidence
Y
Yonggang Zhang
1.0
low confidence
J
Jun Song
1.0
low confidence
Q
Qianshu Cai
1.0
low confidence
D
Dahai Yu
1.0
low confidence
Y
Yike Guo
1.0
low confidence
X
Xinmei Tian
1.0
low confidence
B
Bo Han
1.0
low confidence
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