RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosy
Multi-step retrosynthesis planning seeks to decompose a target molecule into commercially available building blocks through a sequence of feasible reactions. The vast combinatorial search space makes this task challenging even for expert ch
https://arxiv.org/abs/2607.14512v1 ↗Thesis fit
Good fit
Within your typical scope; diligence still required.
In your usual scope
Idea match
Light
How close the company’s idea is to your thesis statement
Sector
llm, 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 ↑ improving
Traction → stable
Idea vs market ↓ declining
▸ Add / edit details
Correct facts used on the next screening or memo.
People
Yanqiao Zhu
US
6.6
low confidence
J
Jingru Gan
2.0
low confidence
X
Xiaoqi Sun
2.0
low confidence
F
Fang Sun
2.0
low confidence
Y
Yidan Shi
1.0
low confidence
M
Md Mofijul Islam
1.0
low confidence
C
Chao Shang
2.0
low confidence
W
Wenhao Gao
2.0
low confidence
C
Connor W. Coley
2.0
low confidence
Y
Yizhou Sun
2.0
low confidence
W
Wei Wang
2.0
low confidence
Y
Y Shi
1.0
low confidence
M
Md Tauhidul Islam
1.0
low confidence
Activity & evidence
Similar baseline plays (YC · idea space)
Adaptyv
· Active
We're building fully automated labs for protein engineering
founders not scraped yet
Ångström AI
· Active
Gen AI molecular simulations that reproduce wetlab results
founders not scraped yet