Step-Level Preference Learning for Generative Agents in Social Simulations
Large language model (LLM)-based generative agents simulate human behavior through long-horizon decision-making processes that comprise intermediate steps such as planning, memory retrieval, reflection, and action selection. However, fine-g
https://arxiv.org/abs/2607.14485v1 ↗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, llm
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 → stable
Traction → stable
Idea vs market ↓ declining
▸ Add / edit details
Correct facts used on the next screening or memo.
People
W
Wenchang Gao
2.0
low confidence
P
Pingyue Sheng
2.0
low confidence
L
Lanlan Qiu
2.0
low confidence
Y
Yunfei Ma
2.0
low confidence
J
Jian Zhao
1.0
low confidence
B
Baicheng Chen
2.0
low confidence
K
Kangda Wang
2.0
low confidence
Y
Yuyang Tian
2.0
low confidence
S
Shunqiang Mao
2.0
low confidence
T
Tianxing He
2.0
low confidence
J
J M Zhao
1.0
low confidence
Activity & evidence
Similar baseline plays (YC · idea space)
Polymath
· Active
Simulation environments to train & evaluate long-horizon AI agents
founders not scraped yet
Social Construct
· Inactive
Social Construct designs and assembles large apartment buildings
…
founders not scraped yet