SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based reinforcement learning (RL) provides a practical optimization pa
https://arxiv.org/abs/2607.14777v1 ↗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
agents, 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 → stable
Traction → stable
Idea vs market ↓ declining
▸ Add / edit details
Correct facts used on the next screening or memo.
People
J
Jinyang Wu
1.0
low confidence
S
Shuo Yang
1.0
low confidence
Z
Zhengxi Lu
1.0
low confidence
F
Fan Zhang
2.0
low confidence
Y
Yuhao Shen
2.0
low confidence
L
Lang Feng
1.0
low confidence
H
Haoran Luo
1.0
low confidence
Z
Zheng Lian
1.0
low confidence
S
Shuai Zhang
1.0
low confidence
Z
Zhengqi Wen
1.0
low confidence
J
Jianhua Tao
1.0
low confidence
Activity & evidence
arXiv
D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding
· authored
signal ▸
Similar baseline plays (YC · idea space)
Unsloth AI
· Active
Open-Source Reinforcement Learning (RL) & Fine-tuning for LLMs.
founders not scraped yet