Author

Junhong Qian

Observed name: Qian, Junhong

Institutions: Shanghai Jiao Tong University, Eastern Institute of Technology, Ningbo, Southeast University

Observed institutions: Shanghai Jiao Tong University, Eastern Institute of Technology, Ningbo, Southeast University

OpenAlex ID: A5137664964

When to Forget: Risk-Controlled Context Adaptation for Long-Horizon Agents

2026 · Chen, Chenle, Wei, Yangbo, et al. · arXiv (Cornell University)

Serve Now or Improve Later? Scheduling Self-Evolution in Online Agent Systems

2026 · Wei, Yangbo, Qian, Junhong, et al. · arXiv (Cornell University)

Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents

2026 · Yao, Chao, Wei, Yangbo, et al. · arXiv (Cornell University)

Competence, Not Accuracy: A Diagnostic for Reference-Free Judge Gates in Skill Optimization

2026 · Chen, Chenle, Wei, Yangbo, et al. · arXiv (Cornell University)

SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems

2026 · Wei, Yangbo, Huang, Zhen, et al. · arXiv (Cornell University)

Works count: 5

Citation count:

H-index:

I10-index: