SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seeking agents. However, as interaction histories grow, agents increasingly struggle to track task progress. When search attempts
https://arxiv.org/abs/2607.15257v1 ↗Thesis fit
Good fit
Within your typical scope; diligence still required.
In your usual scope
Idea match
None
How close the company’s idea is to your thesis statement
Sector
agents, ai
Overlap with sectors you care about
Geography
Outside
Outside your target regions — 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 ↓ declining
▸ Add / edit details
Correct facts used on the next screening or memo.
People
Y
Yuyao Zhang
2.0
low confidence
J
Junjie Gao
2.0
low confidence
Z
Zhengxian Wu
1.0
low confidence
J
Jiaming Fan
2.0
low confidence
J
Jin Zhang
2.0
low confidence
S
Shihan Ma
CN
2.0
low confidence
Y
Yao Yao
2.0
low confidence
W
Weiran Qi
2.0
low confidence
C
Chuyan Jin
1.0
low confidence
G
Guiyu Ma
2.0
low confidence
X
Xingzhong Xu
1.0
low confidence
K
Kai Yang
2.0
low confidence
Z
Z Z Wu
3.0
low confidence
金
金初演
1.0
low confidence
X
X X Xu
2.6
low confidence
Activity & evidence
Enriched
InCarEmo: A Multimodal Dataset for In-Cabin Emotion Recognition and Driver State Monitoring
· authored
signal ▸
Similar baseline plays (YC · idea space)
Firecrawl
· Active
The API to search, scrape, and interact with the web at scale. 🔥
founders not scraped yet