Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Xiaomin Li
Observed names:
Li, Xiaomin,
Lin, Guang
Institutions:
Microsoft (United States),
Harvard University,
The Ohio State University,
Stanford University
Observed institutions:
Microsoft (United States),
Harvard University,
The Ohio State University,
Stanford University
OpenAlex ID:
A5120405738
AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation
2026
·
Sahoo, Priyam
, Mittal, Gaurav
, et al.
·
arXiv (Cornell University)
·
20
PDF
Multi-Rollout On-Policy Distillation via Peer Successes and Failures
2026
·
Yu, Weichen
, Li, Xiaomin
, et al.
·
arXiv (Cornell University)
·
16
PDF
Co-Evolving Skill Generation and Policy Optimization
2026
·
Zhang, Zhiwei
, Lin, Yudi
, et al.
·
arXiv (Cornell University)
·
10
PDF
Bradley-Terry and Multi-Objective Reward Modeling Are Complementary
2025
·
Zhang, Zhiwei
, Liu, Hui
, et al.
·
arXiv (Cornell University)
·
8
PDF
TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning
2026
·
Xu, Yuanda
, Zhou, Zhengze
, et al.
·
arXiv (Cornell University)
·
5
PDF
CONTRAMEM: Learning Self-Evolving Procedural Memory from Contrasting Multi-Model Trajectories
2026
·
Deng, Zheyuan
, Lu, Binghang
, et al.
·
arXiv (Cornell University)
·
2
PDF
ADK Arena: Evaluating Agent Development Kits via LLM-as-a-Developer
2026
·
Huang, Jintao
, Li, Xiaomin
, et al.
·
arXiv (Cornell University)
·
2
PDF
CurveShift: Is Agent Progress Scalar? Separating Level from Shape
2026
·
Xing, Hanwen
, Wang, Pengyun
, et al.
·
arXiv (Cornell University)
·
1
PDF
Show more works
View as search
Works count:
8
Citation count:
64
H-index:
5
I10-index:
3
Year
Topic
Type
