Author

Zihan Lin

Observed name: Lin, Zihan

Institutions: Chinese Academy of Sciences, Institute of Automation, University of Chinese Academy of Sciences

Observed institutions: Chinese Academy of Sciences, Institute of Automation, University of Chinese Academy of Sciences

OpenAlex ID: A5135162302

ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models

2025 · Lin, Zihan, Wang, Xiaohan, et al. · arXiv (Cornell University) · 1

One Step, One Lead: Mitigating Higher-Order Interference in Multi-Domain Reinforcement Learning via Cross-Step Control

2026 · Lin, Zihan, Wang, Xiaohan, et al. · arXiv (Cornell University)

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning

2026 · Lin, Zihan, Wang, Xiaohan, et al. · arXiv (Cornell University)

When Not to Imitate: Boundary-Aware Skill Memory for Reliable Tool-Use LLM Agents

2026 · Zihan Lin, Zhenyu Chen, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)

AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards

2025 · Lin, Zihan, Wang, Xiaohan, et al. · arXiv (Cornell University)

Works count: 5

Citation count: 1

H-index: 1

I10-index: