Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Linji Hao
Observed name:
Hao, Linji
Institutions:
Peking University,
Samsung (China)
Observed institutions:
Peking University,
Samsung (China)
OpenAlex ID:
A5125083570
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
2026
·
Wang, Zi-Han
, Lu, Zhengxi
, et al.
·
arXiv (Cornell University)
·
14
PDF
MeKi: Memory-based Expert Knowledge Injection for Efficient LLM Scaling
2026
·
Ning Ding
, Fangcheng Liu
, et al.
·
Conference on Empirical Methods in Natural Language Processing (EMNLP)
·
8
PDF
JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety
2026
·
Xiong, Yuan
, Hao, Linji
, et al.
·
arXiv (Cornell University)
·
3
PDF
Interlock: From Local Correctness to Task Completion in Long-Horizon Agents
2026
·
Hao, Linji
, He, Yanji
, et al.
·
arXiv (Cornell University)
PDF
ClawLoop: Self-Improving Agents via Harness-Native Training Loop
2026
·
Yang, Hansi
, Hao, Linji
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
5
Citation count:
25
H-index:
3
I10-index:
1
Year
Topic
Type
