Author

Junyao Yang

Observed name: Yang, Junyao

Institutions: National University of Singapore, Tencent (China), Shanghai Artificial Intelligence Laboratory

Observed institutions: National University of Singapore, Tencent (China), Shanghai Artificial Intelligence Laboratory

OpenAlex ID: A5123549519

T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks

2026 · Yang, Junyao, Shi, Yucheng, et al. · arXiv (Cornell University)

Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning

2026 · Yang, Junyao, Shi, Yucheng, et al. · arXiv (Cornell University)

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

2026 · Wang, Ruhan, Shi, Yucheng, et al. · arXiv (Cornell University)

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

2026 · Li, Zongxia, Li, Zhongzhi, et al. · arXiv (Cornell University)

Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models

2026 · Yang, Junyao, Qian, Chen, et al. · arXiv (Cornell University)

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

2026 · Liu, Dongrui, Ren, Qihan, et al. · arXiv (Cornell University)

The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution

2026 · Qian, Chen, Wang, Peng, et al. · arXiv (Cornell University)

ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging

2026 · Yang, Junyao, Qian, Chen, et al. · arXiv (Cornell University)

ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging

2026 · Junyao Yang, Chen Qian, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting

Works count: 9

Citation count:

H-index:

I10-index: