← back

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.

Edit thesis
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
Generate memo
Add / edit details

Correct facts used on the next screening or memo.

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
Perseus · Active
Applied Lab focused on Search in Latent Spaces.
founders not scraped yet
1910 · Active
Multimodal AI Platform for Modality Agnostic Drug Discovery™
founders not scraped yet
Medium Biosciences · Active
AI-designed Affinity Reagents
founders not scraped yet